{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,20]],"date-time":"2026-11-20T17:15:46Z","timestamp":1795194946686,"version":"4.10.3"},"reference-count":215,"publisher":"Association for Computing Machinery (ACM)","issue":"13s","license":[{"start":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T00:00:00Z","timestamp":1689206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"PRIN 2017 project RexLearn","award":["2017TWNMH2"],"award-info":[{"award-number":["2017TWNMH2"]}]},{"name":"Italian Ministry of Education, University and Research"},{"name":"EU\u2019s Horizon Europe research and innovation program under the project ELSA","award":["101070617"],"award-info":[{"award-number":["101070617"]}]},{"name":"\u201cTrustML: Towards Machine Learning that Humans Can Trust,\u201d","award":["F73C22001320007"],"award-info":[{"award-number":["F73C22001320007"]}]},{"name":"Fondazione di Sardegna; the NRRP MUR program funded by the EU - NGEU under the project SERICS","award":["PE00000014"],"award-info":[{"award-number":["PE00000014"]}]},{"name":"COMET Programme managed by FFG in the COMET Module S3AI"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2023,12,31]]},"abstract":"<jats:p>The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative of the data that will be encountered at test time. This assumption is challenged by the threat of poisoning, an attack that manipulates the training data to compromise the model\u2019s performance at test time. Although poisoning has been acknowledged as a relevant threat in industry applications, and a variety of different attacks and defenses have been proposed so far, a complete systematization and critical review of the field is still missing. In this survey, we provide a comprehensive systematization of poisoning attacks and defenses in machine learning, reviewing more than 100 papers published in the field in the past 15 years. We start by categorizing the current threat models and attacks and then organize existing defenses accordingly. While we focus mostly on computer-vision applications, we argue that our systematization also encompasses state-of-the-art attacks and defenses for other data modalities. Finally, we discuss existing resources for research in poisoning and shed light on the current limitations and open research questions in this research field.<\/jats:p>","DOI":"10.1145\/3585385","type":"journal-article","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T07:04:09Z","timestamp":1677654249000},"page":"1-39","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":156,"title":["Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning"],"prefix":"10.1145","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3807-6417","authenticated-orcid":false,"given":"Antonio Emanuele","family":"Cin\u00e0","sequence":"first","affiliation":[{"name":"DAIS, Ca\u2019 Foscari University of Venice, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5401-4171","authenticated-orcid":false,"given":"Kathrin","family":"Grosse","sequence":"additional","affiliation":[{"name":"VITA Lab, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9318-6913","authenticated-orcid":false,"given":"Ambra","family":"Demontis","sequence":"additional","affiliation":[{"name":"DIEE, University of Cagliari, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7855-1641","authenticated-orcid":false,"given":"Sebastiano","family":"Vascon","sequence":"additional","affiliation":[{"name":"DAIS, Ca\u2019 Foscari University of Venice and European Center for Living Technology, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1166-6062","authenticated-orcid":false,"given":"Werner","family":"Zellinger","sequence":"additional","affiliation":[{"name":"Software Competence Center Hagenberg GmbH (SCCH), Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1859-046X","authenticated-orcid":false,"given":"Bernhard A.","family":"Moser","sequence":"additional","affiliation":[{"name":"Software Competence Center Hagenberg GmbH (SCCH), Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4979-5292","authenticated-orcid":false,"given":"Alina","family":"Oprea","sequence":"additional","affiliation":[{"name":"Khoury College of Computer Sciences, Northeastern University, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7752-509X","authenticated-orcid":false,"given":"Battista","family":"Biggio","sequence":"additional","affiliation":[{"name":"DIEE, University of Cagliari, CINI, and Pluribus One, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8992-9243","authenticated-orcid":false,"given":"Marcello","family":"Pelillo","sequence":"additional","affiliation":[{"name":"DAIS, Ca\u2019 Foscari University of Venice, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4103-9190","authenticated-orcid":false,"given":"Fabio","family":"Roli","sequence":"additional","affiliation":[{"name":"DIBRIS, University of Genoa, CINI, and Pluribus One, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,7,13]]},"reference":[{"key":"e_1_3_3_2_2","article-title":"VENOMAVE: Clean-label poisoning against speech recognition","author":"Aghakhani Hojjat","year":"2020","unstructured":"Hojjat Aghakhani, Thorsten Eisenhofer, Lea Sch\u00f6nherr, Dorothea Kolossa, Thorsten Holz, Christopher Kruegel, and Giovanni Vigna. 2020. VENOMAVE: Clean-label poisoning against speech recognition. arXiv:2010.10682 (2020).","journal-title":"arXiv:2010.10682"},{"key":"e_1_3_3_3_2","first-page":"159","volume-title":"European Symposium on Security and Privacy (EuroS&P)","author":"Aghakhani Hojjat","year":"2021","unstructured":"Hojjat Aghakhani, Dongyu Meng, Yu-Xiang Wang, Christopher Kruegel, and Giovanni Vigna. 2021. Bullseye polytope: A scalable clean-label poisoning attack with improved transferability. In European Symposium on Security and Privacy (EuroS&P). 159\u2013178."},{"key":"e_1_3_3_4_2","article-title":"Poisoning deep reinforcement learning agents with in-distribution triggers","author":"Ashcraft Chace","year":"2021","unstructured":"Chace Ashcraft and Kiran Karra. 2021. Poisoning deep reinforcement learning agents with in-distribution triggers. arXiv:2106.07798 (2021).","journal-title":"arXiv:2106.07798"},{"key":"e_1_3_3_5_2","first-page":"2938","volume-title":"23rd International Conference on AI and Statistics","author":"Bagdasaryan Eugene","year":"2020","unstructured":"Eugene Bagdasaryan, Andreas Veit, Yiqing Hua, Deborah Estrin, and Vitaly Shmatikov. 2020. How to backdoor federated learning. In 23rd International Conference on AI and Statistics. PMLR, 2938\u20132948."},{"key":"e_1_3_3_6_2","article-title":"Baseline pruning-based approach to trojan detection in neural networks","author":"Bajcsy Peter","year":"2021","unstructured":"Peter Bajcsy and Michael Majurski. 2021. Baseline pruning-based approach to trojan detection in neural networks. arXiv:2101.12016 (2021).","journal-title":"arXiv:2101.12016"},{"key":"e_1_3_3_7_2","article-title":"Defense against reward poisoning attacks in reinforcement learning","author":"Banihashem Kiarash","year":"2021","unstructured":"Kiarash Banihashem, Adish Singla, and Goran Radanovic. 2021. Defense against reward poisoning attacks in reinforcement learning. arXiv:2102.05776 (2021).","journal-title":"arXiv:2102.05776"},{"key":"e_1_3_3_8_2","first-page":"57","volume-title":"IEEE International Congress on Internet of Things","author":"Baracaldo Nathalie","year":"2018","unstructured":"Nathalie Baracaldo, Bryant Chen, Heiko Ludwig, Amir Safavi, and Rui Zhang. 2018. Detecting poisoning attacks on ML in IoT environments. In IEEE International Congress on Internet of Things. IEEE, 57\u201364."},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8802997"},{"key":"e_1_3_3_10_2","first-page":"16","volume-title":"ACM Symposium on Information, Computer and Communications Security","author":"Barreno Marco","year":"2006","unstructured":"Marco Barreno, Blaine Nelson, Russell Sears, Anthony D. Joseph, and J. D. Tygar. 2006. Can ML be secure? In ACM Symposium on Information, Computer and Communications Security. ACM, 16\u201325."},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-62416-7_19"},{"issue":"2","key":"e_1_3_3_12_2","article-title":"Random search for hyper-parameter optimization.","volume":"13","author":"Bergstra James","year":"2012","unstructured":"James Bergstra and Yoshua Bengio. 2012. Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13, 2 (2012).","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_3_13_2","first-page":"634","volume-title":"36th International Conference on Machine Learning","author":"Bhagoji Arjun Nitin","year":"2019","unstructured":"Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal, and Seraphin B. Calo. 2019. Analyzing federated learning through an adversarial lens. In 36th International Conference on Machine Learning. PMLR, 634\u2013643."},{"key":"e_1_3_3_14_2","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1007\/978-3-642-21557-5_37","volume-title":"International Workshop on Multiple Classifier Systems.","author":"Biggio Battista","year":"2011","unstructured":"Battista Biggio, Igino Corona, Giorgio Fumera, Giorgio Giacinto, and Fabio Roli. 2011. Bagging classifiers for fighting poisoning attacks in adversarial classification tasks. In International Workshop on Multiple Classifier Systems. Springer, 350\u2013359."},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_25"},{"key":"e_1_3_3_16_2","first-page":"97","volume-title":"ACML2011","author":"Biggio Battista","year":"2011","unstructured":"Battista Biggio, Blaine Nelson, and Pavel Laskov. 2011. Support vector machines under adversarial label noise. In ACML2011. 97\u2013112."},{"key":"e_1_3_3_17_2","volume-title":"International Conference on Machine Learning","author":"Biggio Battista","year":"2012","unstructured":"Battista Biggio, Blaine Nelson, and Pavel Laskov. 2012. Poisoning attacks against support vector machines. In International Conference on Machine Learning."},{"key":"e_1_3_3_18_2","first-page":"87","volume-title":"6th ACM Workshop on Artificial Intelligence and Security 2013","author":"Biggio Battista","year":"2013","unstructured":"Battista Biggio, Ignazio Pillai, Samuel Rota Bul\u00f2, Davide Ariu, Marcello Pelillo, and Fabio Roli. 2013. Is data clustering in adversarial settings secure? In 6th ACM Workshop on Artificial Intelligence and Security 2013. ACM, 87\u201398."},{"key":"e_1_3_3_19_2","first-page":"27","volume-title":"7th ACM Workshop on Artificial Intelligence and Security","author":"Biggio Battista","year":"2014","unstructured":"Battista Biggio, Konrad Rieck, Davide Ariu, Christian Wressnegger, Igino Corona, Giorgio Giacinto, and Fabio Roli. 2014. Poisoning behavioral malware clustering. In 7th ACM Workshop on Artificial Intelligence and Security. ACM, 27\u201336."},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.023"},{"key":"e_1_3_3_21_2","first-page":"695","volume-title":"International Conference on Machine Learning","author":"Bojchevski Aleksandar","year":"2019","unstructured":"Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2019. Adversarial attacks on node embeddings via graph poisoning. In International Conference on Machine Learning. 695\u2013704."},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414862"},{"key":"e_1_3_3_23_2","article-title":"DP-InstaHide: Provably defusing poisoning and backdoor attacks with differentially private data augmentations","author":"Borgnia Eitan","year":"2021","unstructured":"Eitan Borgnia, Jonas Geiping, Valeriia Cherepanova, Liam Fowl, Arjun Gupta, Amin Ghiasi, Furong Huang, Micah Goldblum, and Tom Goldstein. 2021. DP-InstaHide: Provably defusing poisoning and backdoor attacks with differentially private data augmentations. arXiv:2103.02079 (2021).","journal-title":"arXiv:2103.02079"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS47876.2019.00042"},{"key":"e_1_3_3_25_2","article-title":"On evaluating adversarial robustness","author":"Carlini Nicholas","year":"2019","unstructured":"Nicholas Carlini, Anish Athalye, Nicolas Papernot, Wieland Brendel, Jonas Rauber, Dimitris Tsipras, Ian Goodfellow, Aleksander Madry, and Alexey Kurakin. 2019. On evaluating adversarial robustness. arXiv:1902.06705 (2019).","journal-title":"arXiv:1902.06705"},{"key":"e_1_3_3_26_2","article-title":"Regularization can help mitigate poisoning attacks... with the right hyperparameters","author":"Carnerero-Cano Javier","year":"2021","unstructured":"Javier Carnerero-Cano, Luis Mu\u00f1oz-Gonz\u00e1lez, Phillippa Spencer, and Emil C. Lupu. 2021. Regularization can help mitigate poisoning attacks... with the right hyperparameters. arXiv:2105.10948 (2021).","journal-title":"arXiv:2105.10948"},{"key":"e_1_3_3_27_2","article-title":"Adversarial attacks and defences: A survey","author":"Chakraborty Anirban","year":"2018","unstructured":"Anirban Chakraborty, Manaar Alam, Vishal Dey, Anupam Chattopadhyay, and Debdeep Mukhopadhyay. 2018. Adversarial attacks and defences: A survey. arXiv:1810.00069 (2018).","journal-title":"arXiv:1810.00069"},{"key":"e_1_3_3_28_2","article-title":"Property inference from poisoning","author":"Chase Melissa","year":"2021","unstructured":"Melissa Chase, Esha Ghosh, and Saeed Mahloujifar. 2021. Property inference from poisoning. arXiv:2101.11073 (2021).","journal-title":"arXiv:2101.11073"},{"key":"e_1_3_3_29_2","article-title":"Detecting backdoor attacks on deep neural networks by activation clustering","author":"Chen Bryant","year":"2018","unstructured":"Bryant Chen, Wilka Carvalho, Nathalie Baracaldo, Heiko Ludwig, Benjamin Edwards, Taesung Lee, Ian Molloy, and Biplav Srivastava. 2018. Detecting backdoor attacks on deep neural networks by activation clustering. arXiv:1811.03728 (2018).","journal-title":"arXiv:1811.03728"},{"key":"e_1_3_3_30_2","article-title":"Mitigating backdoor attacks in LSTM-based text classification sys. by backdoor keyword identification","author":"Chen Chuanshuai","year":"2020","unstructured":"Chuanshuai Chen and Jiazhu Dai. 2020. Mitigating backdoor attacks in LSTM-based text classification sys. by backdoor keyword identification. arXiv:2007.12070 (2020).","journal-title":"arXiv:2007.12070"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/647"},{"key":"e_1_3_3_32_2","first-page":"15","volume-title":"10th ACM Workshop on AI and Security (AISec\u201917)","author":"Chen Pin-Yu","year":"2017","unstructured":"Pin-Yu Chen, Huan Zhang, Yash Sharma, Jinfeng Yi, and Cho-Jui Hsieh. 2017. ZOO: Zeroth order optimization based black-box attacks to deep neural networks without training substitute models. In 10th ACM Workshop on AI and Security (AISec\u201917). 15\u201326."},{"key":"e_1_3_3_33_2","volume-title":"International Conference on Machine Learning","author":"Chen Ruoxin","year":"2022","unstructured":"Ruoxin Chen, Zenan Li, Jie Li, Junchi Yan, and Chentao Wu. 2022. On collective robustness of bagging against data poisoning. In International Conference on Machine Learning."},{"key":"e_1_3_3_34_2","article-title":"Targeted backdoor attacks on deep learning systems using data poisoning","author":"Chen Xinyun","year":"2017","unstructured":"Xinyun Chen, Chang Liu, Bo Li, Kimberly Lu, and Dawn Song. 2017. Targeted backdoor attacks on deep learning systems using data poisoning. arXiv:1712.05526 (2017).","journal-title":"arXiv:1712.05526"},{"key":"e_1_3_3_35_2","volume-title":"International Conference on Machine Learning Workshop on Adversarial Machine Learning","author":"Chen Xiaoyi","year":"2021","unstructured":"Xiaoyi Chen, Ahmed Salem, Michael Backes, Shiqing Ma, and Yang Zhang. 2021. BadNL: Backdoor attacks against NLP models. In International Conference on Machine Learning Workshop on Adversarial Machine Learning."},{"key":"e_1_3_3_36_2","article-title":"Defending against backdoor attack on deep neural networks","author":"Cheng Hao","year":"2020","unstructured":"Hao Cheng, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Pu Zhao, and Xue Lin. 2020. Defending against backdoor attack on deep neural networks. arXiv:2002.12162 (2020).","journal-title":"arXiv:2002.12162"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16201"},{"key":"e_1_3_3_38_2","first-page":"48","volume-title":"IEEE Security and Privacy Workshops","author":"Chou Edward","year":"2020","unstructured":"Edward Chou, Florian Tramer, and Giancarlo Pellegrino. 2020. SentiNet: Detecting localized universal attacks against deep learning systems. In IEEE Security and Privacy Workshops. IEEE, 48\u201354."},{"key":"e_1_3_3_39_2","article-title":"Energy-latency attacks via sponge poisoning","author":"Cin\u00e0 Antonio Emanuele","year":"2022","unstructured":"Antonio Emanuele Cin\u00e0, Ambra Demontis, Battista Biggio, Fabio Roli, and Marcello Pelillo. 2022. Energy-latency attacks via sponge poisoning. arXiv:2203.08147 (2022).","journal-title":"arXiv:2203.08147"},{"key":"e_1_3_3_40_2","article-title":"Machine learning security against data poisoning: Are we there yet?","volume":"2204","author":"Cin\u00e0 Antonio Emanuele","year":"2022","unstructured":"Antonio Emanuele Cin\u00e0, Kathrin Grosse, Ambra Demontis, Battista Biggio, Fabio Roli, and Marcello Pelillo. 2022. Machine learning security against data poisoning: Are we there yet? CoRR abs\/2204.05986 (2022).","journal-title":"CoRR"},{"key":"e_1_3_3_41_2","article-title":"Backdoor learning curves: Explaining backdoor poisoning beyond influence functions","author":"Cin\u00e0 Antonio Emanuele","year":"2021","unstructured":"Antonio Emanuele Cin\u00e0, Kathrin Grosse, Sebastiano Vascon, Ambra Demontis, Battista Biggio, Fabio Roli, and Marcello Pelillo. 2021. Backdoor learning curves: Explaining backdoor poisoning beyond influence functions. arXiv:2106.07214 (2021).","journal-title":"arXiv:2106.07214"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108306"},{"key":"e_1_3_3_43_2","first-page":"1","volume-title":"International Joint Conference on Neural Networks","author":"Cin\u00e0 Antonio Emanuele","year":"2021","unstructured":"Antonio Emanuele Cin\u00e0, Sebastiano Vascon, Ambra Demontis, Battista Biggio, Fabio Roli, and Marcello Pelillo. 2021. The hammer and the nut: Is bilevel optimization really needed to poison linear classifiers? In International Joint Conference on Neural Networks. IEEE, 1\u20138."},{"key":"e_1_3_3_44_2","first-page":"81","volume-title":"IEEE Symposium on Security and Privacy","author":"Cretu G. F.","year":"2008","unstructured":"G. F. Cretu, A. Stavrou, M. E. Locasto, S. J. Stolfo, and A. D. Keromytis. 2008. Casting out demons: Sanitizing training data for anomaly sensors. In IEEE Symposium on Security and Privacy. 81\u201395."},{"key":"e_1_3_3_45_2","series-title":"Italian Conference on Cybersecurity","first-page":"106","volume":"1816","author":"Demontis Ambra","year":"2017","unstructured":"Ambra Demontis, Battista Biggio, Giorgio Fumera, Giorgio Giacinto, and Fabio Roli. 2017. Infinity-norm support vector machines against adversarial label contamination. In Italian Conference on Cybersecurity(CEUR Workshop Proceedings, Vol. 1816). CEUR-WS.org, 106\u2013115."},{"key":"e_1_3_3_46_2","first-page":"321","volume-title":"USENIX Security Symposium.","author":"Demontis Ambra","year":"2019","unstructured":"Ambra Demontis, Marco Melis, Maura Pintor, Matthew Jagielski, Battista Biggio, Alina Oprea, Cristina Nita-Rotaru, and Fabio Roli. 2019. Why do adversarial attacks transfer? Explaining transferability of evasion and poisoning attacks. In USENIX Security Symposium.USENIX Association, 321\u2013338."},{"key":"e_1_3_3_47_2","first-page":"1596","volume-title":"International Conference on Machine Learning","author":"Diakonikolas Ilias","year":"2019","unstructured":"Ilias Diakonikolas, Gautam Kamath, Daniel Kane, Jerry Li, Jacob Steinhardt, and Alistair Stewart. 2019. Sever: A robust meta-algorithm for stochastic optimization. In International Conference on Machine Learning. PMLR, 1596\u20131606."},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3427228.3427264"},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01175"},{"key":"e_1_3_3_50_2","first-page":"318","volume-title":"15th International Conference on Artificial Intelligence and Statistics","author":"Domke Justin","year":"2012","unstructured":"Justin Domke. 2012. Generic methods for optimization-based modeling. In 15th International Conference on Artificial Intelligence and Statistics. JMLR, 318\u2013326."},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01617"},{"key":"e_1_3_3_52_2","volume-title":"International Conference on Learning Representations","author":"Du Min","year":"2020","unstructured":"Min Du, Ruoxi Jia, and Dawn Song. 2020. Robust anomaly detection and backdoor attack detection via differential privacy. In International Conference on Learning Representations."},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/656"},{"key":"e_1_3_3_54_2","volume-title":"NeurIPS","author":"Feng Ji","year":"2019","unstructured":"Ji Feng, Qi-Zhi Cai, and Zhi-Hua Zhou. 2019. Learning to confuse: Generating training time adversarial data with auto-encoder. In NeurIPS."},{"key":"e_1_3_3_55_2","first-page":"253","volume-title":"International Conference on Advances in Neural Information Processing Systems","author":"Feng Jiashi","year":"2014","unstructured":"Jiashi Feng, Huan Xu, Shie Mannor, and Shuicheng Yan. 2014. Robust logistic regression and classification. In International Conference on Advances in Neural Information Processing Systems. 253\u2013261."},{"key":"e_1_3_3_56_2","article-title":"Preventing unauthorized use of proprietary data: Poisoning for secure dataset release","author":"Fowl Liam","year":"2021","unstructured":"Liam Fowl, Ping-yeh Chiang, Micah Goldblum, Jonas Geiping, Arpit Bansal, Wojtek Czaja, and Tom Goldstein. 2021. Preventing unauthorized use of proprietary data: Poisoning for secure dataset release. arXiv:2103.02683 (2021).","journal-title":"arXiv:2103.02683"},{"key":"e_1_3_3_57_2","article-title":"Adversarial examples make strong poisons","author":"Fowl Liam","year":"2021","unstructured":"Liam Fowl, Micah Goldblum, Ping-yeh Chiang, Jonas Geiping, Wojtek Czaja, and Tom Goldstein. 2021. Adversarial examples make strong poisons. arXiv:2106.10807.","journal-title":"arXiv:2106.10807"},{"key":"e_1_3_3_58_2","first-page":"1563","volume-title":"International Conference on Machine Learning","volume":"80","author":"Franceschi Luca","year":"2018","unstructured":"Luca Franceschi, Paolo Frasconi, Saverio Salzo, Riccardo Grazzi, and Massimiliano Pontil. 2018. Bilevel programming for hyperparameter optimization and meta-learning. In International Conference on Machine Learning, Vol. 80. PMLR, 1563\u20131572."},{"key":"e_1_3_3_59_2","first-page":"1","volume-title":"International Joint Conference on Neural Networks","author":"Frederickson Christopher","year":"2018","unstructured":"Christopher Frederickson, Michael Moore, Glenn Dawson, and Robi Polikar. 2018. Attack strength vs. detectability dilemma in adversarial ML. In International Joint Conference on Neural Networks. IEEE, 1\u20138."},{"key":"e_1_3_3_60_2","article-title":"Backdoor attacks and countermeasures on deep learning: A comprehensive review","author":"Gao Yansong","year":"2020","unstructured":"Yansong Gao, Bao Gia Doan, Zhi Zhang, Siqi Ma, Jiliang Zhang, Anmin Fu, Surya Nepal, and Hyoungshick Kim. 2020. Backdoor attacks and countermeasures on deep learning: A comprehensive review. arXiv:2007.10760 (2020).","journal-title":"arXiv:2007.10760"},{"key":"e_1_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3359789.3359790"},{"key":"e_1_3_3_62_2","article-title":"What doesn\u2019t kill you makes you robust (er): Adversarial training against poisons and backdoors","author":"Geiping Jonas","year":"2021","unstructured":"Jonas Geiping, Liam Fowl, Gowthami Somepalli, Micah Goldblum, Michael Moeller, and Tom Goldstein. 2021. What doesn\u2019t kill you makes you robust (er): Adversarial training against poisons and backdoors. arXiv:2102.13624 (2021).","journal-title":"arXiv:2102.13624"},{"key":"e_1_3_3_63_2","volume-title":"International Conference on Learning Representations","author":"Geiping Jonas","year":"2021","unstructured":"Jonas Geiping, Liam H. Fowl, W. Ronny Huang, Wojciech Czaja, Gavin Taylor, Michael Moeller, and Tom Goldstein. 2021. Witches\u2019 brew: Industrial scale data poisoning via gradient matching. In International Conference on Learning Representations. OpenReview."},{"key":"e_1_3_3_64_2","article-title":"Motivating the rules of the game for adversarial example research","author":"Gilmer Justin","year":"2018","unstructured":"Justin Gilmer, Ryan P. Adams, Ian Goodfellow, David Andersen, and George E. Dahl. 2018. Motivating the rules of the game for adversarial example research. arXiv:1807.06732 (2018).","journal-title":"arXiv:1807.06732"},{"key":"e_1_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3162397"},{"key":"e_1_3_3_66_2","article-title":"Planting undetectable backdoors in machine learning models","author":"Goldwasser Shafi","year":"2022","unstructured":"Shafi Goldwasser, Michael P. Kim, Vinod Vaikuntanathan, and Or Zamir. 2022. Planting undetectable backdoors in machine learning models. arXiv:2204.06974 (2022).","journal-title":"arXiv:2204.06974"},{"key":"e_1_3_3_67_2","volume-title":"International Conference on Learning Representations 2015","author":"Goodfellow Ian J.","year":"2015","unstructured":"Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy. 2015. Explaining and harnessing adversarial examples. In International Conference on Learning Representations 2015."},{"key":"e_1_3_3_68_2","article-title":"Advbox: A toolbox to generate adversarial examples that fool neural networks","author":"Goodman Dou","year":"2020","unstructured":"Dou Goodman, Hao Xin, Wang Yang, Wu Yuesheng, Xiong Junfeng, and Zhang Huan. 2020. Advbox: A toolbox to generate adversarial examples that fool neural networks. arXiv:2001.05574 (2020).","journal-title":"arXiv:2001.05574"},{"key":"e_1_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3251842"},{"key":"e_1_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2022.102814"},{"key":"e_1_3_3_71_2","article-title":"BadNets: Identifying vulnerabilities in the ML model supply chain","author":"Gu Tianyu","year":"2017","unstructured":"Tianyu Gu, Brendan Dolan-Gavitt, and Siddharth Garg. 2017. BadNets: Identifying vulnerabilities in the ML model supply chain. arXiv (2017).","journal-title":"arXiv"},{"key":"e_1_3_3_72_2","volume-title":"International Conference on Learning Representations","author":"Guo Junfeng","year":"2022","unstructured":"Junfeng Guo, Ang Li, and Cong Liu. 2022. AEVA: Black-box backdoor detection using adversarial extreme value analysis. In International Conference on Learning Representations."},{"key":"e_1_3_3_73_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_9"},{"key":"e_1_3_3_74_2","article-title":"Tabor: A highly accurate approach to inspecting and restoring trojan backdoors in AI systems","author":"Guo Wenbo","year":"2019","unstructured":"Wenbo Guo, Lun Wang, Xinyu Xing, Min Du, and Dawn Song. 2019. Tabor: A highly accurate approach to inspecting and restoring trojan backdoors in AI systems. arXiv:1908.01763 (2019).","journal-title":"arXiv:1908.01763"},{"key":"e_1_3_3_75_2","first-page":"1","volume-title":"International Joint Conference on Neural Networks","author":"Han Yi","year":"2020","unstructured":"Yi Han, David Hubczenko, Paul Montague, Olivier De Vel, Tamas Abraham, Benjamin I. P. Rubinstein, Christopher Leckie, Tansu Alpcan, and Sarah Erfani. 2020. Adversarial reinforcement learning under partial observability in autonomous computer network defence. In International Joint Conference on Neural Networks. IEEE, 1\u20138."},{"key":"e_1_3_3_76_2","first-page":"4129","volume-title":"International Conference on Machine Learning","author":"Hayase Jonathan","year":"2021","unstructured":"Jonathan Hayase, Weihao Kong, Raghav Somani, and Sewoong Oh. 2021. SPECTRE: Defending against backdoor attacks using robust statistics. In International Conference on Machine Learning. PMLR, 4129\u20134139."},{"key":"e_1_3_3_77_2","first-page":"6604","article-title":"Contamination attacks and mitigation in multi-party ML","volume":"31","author":"Hayes Jamie","year":"2018","unstructured":"Jamie Hayes and Olga Ohrimenko. 2018. Contamination attacks and mitigation in multi-party ML. Adv. Neural Inf. Proc Syst. 31 (2018), 6604\u20136615.","journal-title":"Adv. Neural Inf. Proc Syst."},{"key":"e_1_3_3_78_2","article-title":"On the effectiveness of mitigating data poisoning attacks with gradient shaping","author":"Hong Sanghyun","year":"2020","unstructured":"Sanghyun Hong, Varun Chandrasekaran, Yi\u011fitcan Kaya, Tudor Dumitra\u015f, and Nicolas Papernot. 2020. On the effectiveness of mitigating data poisoning attacks with gradient shaping. arXiv:2002.11497 (2020).","journal-title":"arXiv:2002.11497"},{"key":"e_1_3_3_79_2","volume-title":"International Conference on Learning Representations","author":"Hu Xiaoling","year":"2022","unstructured":"Xiaoling Hu, Xiao Lin, Michael Cogswell, Yi Yao, Susmit Jha, and Chao Chen. 2022. Trigger hunting with a topological prior for trojan detection. In International Conference on Learning Representations."},{"key":"e_1_3_3_80_2","volume-title":"International Conference on Learning Representations","author":"Huang Kunzhe","year":"2022","unstructured":"Kunzhe Huang, Yiming Li, Baoyuan Wu, Zhan Qin, and Kui Ren. 2022. Backdoor defense via decoupling the training process. In International Conference on Learning Representations."},{"key":"e_1_3_3_81_2","volume-title":"International Conference on Advances in Neural Information Processing Systems","author":"Huang W. Ronny","year":"2020","unstructured":"W. Ronny Huang, Jonas Geiping, Liam Fowl, Gavin Taylor, and Tom Goldstein. 2020. MetaPoison: Practical general-purpose clean-label data poisoning. In International Conference on Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_82_2","article-title":"NeuronInspect: Detecting backdoors in neural networks via output explanations","author":"Huang Xijie","year":"2019","unstructured":"Xijie Huang, Moustafa Alzantot, and Mani Srivastava. 2019. NeuronInspect: Detecting backdoors in neural networks via output explanations. arXiv:1911.07399 (2019).","journal-title":"arXiv:1911.07399"},{"key":"e_1_3_3_83_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32430-8_14"},{"key":"e_1_3_3_84_2","first-page":"19","volume-title":"IEEE Symposium on Security and Privacy","author":"Jagielski Matthew","year":"2018","unstructured":"Matthew Jagielski, Alina Oprea, Battista Biggio, Chang Liu, Cristina Nita-Rotaru, and Bo Li. 2018. Manipulating ML: Poisoning attacks and countermeasures for regression learning. In IEEE Symposium on Security and Privacy. IEEE, 19\u201335."},{"key":"e_1_3_3_85_2","doi-asserted-by":"publisher","DOI":"10.1145\/3460120.3485368"},{"key":"e_1_3_3_86_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415671"},{"key":"e_1_3_3_87_2","article-title":"Certified robustness of nearest neighbors against data poisoning attacks","author":"Jia Jinyuan","year":"2020","unstructured":"Jinyuan Jia, Xiaoyu Cao, and Neil Zhenqiang Gong. 2020. Certified robustness of nearest neighbors against data poisoning attacks. arXiv (2020).","journal-title":"arXiv"},{"key":"e_1_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008306431147"},{"key":"e_1_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.133"},{"key":"e_1_3_3_90_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218663"},{"key":"e_1_3_3_91_2","first-page":"405","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Kloft Marius","year":"2010","unstructured":"Marius Kloft and Pavel Laskov. 2010. Online anomaly detection under adversarial impact. In International Conference on Artificial Intelligence and Statistics. JMLR, 405\u2013412."},{"key":"e_1_3_3_92_2","article-title":"Can you hear it? Backdoor attacks via ultrasonic triggers","author":"Koffas Stefanos","year":"2021","unstructured":"Stefanos Koffas, Jing Xu, Mauro Conti, and Stjepan Picek. 2021. Can you hear it? Backdoor attacks via ultrasonic triggers. arXiv (2021).","journal-title":"arXiv"},{"key":"e_1_3_3_93_2","first-page":"1885","volume-title":"International Conference on Machine Learning","author":"Koh Pang Wei","year":"2017","unstructured":"Pang Wei Koh and Percy Liang. 2017. Understanding black-box predictions via influence functions. In International Conference on Machine Learning. PMLR, 1885\u20131894."},{"key":"e_1_3_3_94_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06119-y"},{"key":"e_1_3_3_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00038"},{"key":"e_1_3_3_96_2","doi-asserted-by":"crossref","unstructured":"Ram Shankar Siva Kumar Magnus Nystr\u00f6m John Lambert Andrew Marshall Mario Goertzel Andi Comissoneru Matt Swann and Sharon Xia. 2020. Adversarial ML-industry perspectives. (2020) 69\u201375.","DOI":"10.1109\/SPW50608.2020.00028"},{"key":"e_1_3_3_97_2","article-title":"Curie: A method for protecting SVM classifier from poisoning attack","author":"Laishram Ricky","year":"2016","unstructured":"Ricky Laishram and Vir Virander Phoha. 2016. Curie: A method for protecting SVM classifier from poisoning attack. arXiv:1606.01584 (2016).","journal-title":"arXiv:1606.01584"},{"key":"e_1_3_3_98_2","volume-title":"International Conference on Learning Representations","author":"Levine Alexander","year":"2021","unstructured":"Alexander Levine and Soheil Feizi. 2021. Deep partition aggregation: Provable defenses against general poisoning attacks. In International Conference on Learning Representations."},{"key":"e_1_3_3_99_2","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3242042"},{"key":"e_1_3_3_100_2","first-page":"1","article-title":"Invisible backdoor attacks on deep neural networks via steganography and regularization","author":"Li Shaofeng","year":"2020","unstructured":"Shaofeng Li, Minhui Xue, Benjamin Zhao, Haojin Zhu, and Xinpeng Zhang. 2020. Invisible backdoor attacks on deep neural networks via steganography and regularization. IEEE Trans. Depend. Sec. Comput. PP (092020), 1\u20131.","journal-title":"IEEE Trans. Depend. Sec. Comput."},{"key":"e_1_3_3_101_2","article-title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","author":"Li Yige","year":"2021","unstructured":"Yige Li, Nodens Koren, Lingjuan Lyu, Xixiang Lyu, Bo Li, and Xingjun Ma. 2021. Neural attention distillation: Erasing backdoor triggers from deep neural networks. In International Conference on Learning Representations.","journal-title":"International Conference on Learning Representations"},{"key":"e_1_3_3_102_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01615"},{"key":"e_1_3_3_103_2","article-title":"Anti-backdoor learning: Training clean models on poisoned data","author":"Li Yige","year":"2021","unstructured":"Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, and Xingjun Ma. 2021. Anti-backdoor learning: Training clean models on poisoned data. In International Conference on Advances in Neural Information Processing Systems.","journal-title":"International Conference on Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_104_2","article-title":"Backdoor learning: A survey","author":"Li Yiming","year":"2020","unstructured":"Yiming Li, Baoyuan Wu, Yong Jiang, Zhifeng Li, and Shu-Tao Xia. 2020. Backdoor learning: A survey. arXiv:2007.08745 (2020).","journal-title":"arXiv:2007.08745"},{"key":"e_1_3_3_105_2","article-title":"Rethinking the trigger of backdoor attack","author":"Li Yiming","year":"2020","unstructured":"Yiming Li, Tongqing Zhai, Baoyuan Wu, Yong Jiang, Zhifeng Li, and Shutao Xia. 2020. Rethinking the trigger of backdoor attack. arXiv (2020).","journal-title":"arXiv"},{"key":"e_1_3_3_106_2","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3423362"},{"key":"e_1_3_3_107_2","first-page":"91","volume-title":"10th ACM Workshop on Artificial Intelligence and Security","author":"Liu Chang","year":"2017","unstructured":"Chang Liu, Bo Li, Yevgeniy Vorobeychik, and Alina Oprea. 2017. Robust linear regression against training data poisoning. In 10th ACM Workshop on Artificial Intelligence and Security. ACM, 91\u2013102."},{"key":"e_1_3_3_108_2","first-page":"273","volume-title":"International Symposium on Research in Attacks, Intrusions, and Defenses","author":"Liu Kang","year":"2018","unstructured":"Kang Liu, Brendan Dolan-Gavitt, and Siddharth Garg. 2018. Fine-pruning: Defending against backdooring attacks on deep neural networks. In International Symposium on Research in Attacks, Intrusions, and Defenses. Springer, 273\u2013294."},{"key":"e_1_3_3_109_2","first-page":"9777","volume-title":"International Conference on Advances in Neural Information Processing Systems","author":"Liu Xuanqing","year":"2019","unstructured":"Xuanqing Liu, Si Si, Jerry Zhu, Yang Li, and Cho-Jui Hsieh. 2019. A unified framework for data poisoning attack to graph-based semi-supervised learning. In International Conference on Advances in Neural Information Processing Systems. 9777\u20139787."},{"key":"e_1_3_3_110_2","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3363216"},{"key":"e_1_3_3_111_2","first-page":"45","volume-title":"Network and Distributed System Security Symposium","author":"Liu Yingqi","year":"2018","unstructured":"Yingqi Liu, Shiqing Ma, Yousra Aafer, Wen-Chuan Lee, Juan Zhai, Weihang Wang, and Xiangyu Zhang. 2018. Trojaning attack on neural networks. In Network and Distributed System Security Symposium. 45\u201348."},{"key":"e_1_3_3_112_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_11"},{"key":"e_1_3_3_113_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2017.16"},{"key":"e_1_3_3_114_2","doi-asserted-by":"publisher","DOI":"10.1145\/3071178.3071208"},{"key":"e_1_3_3_115_2","first-page":"1540","volume-title":"International Conference on AI and Statistics","author":"Lorraine Jonathan","year":"2020","unstructured":"Jonathan Lorraine, Paul Vicol, and David Duvenaud. 2020. Optimizing millions of hyperparameters by implicit differentiation. In International Conference on AI and Statistics. PMLR, 1540\u20131552."},{"key":"e_1_3_3_116_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01554-1_11"},{"key":"e_1_3_3_117_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/657"},{"key":"e_1_3_3_118_2","first-page":"2113","volume-title":"32nd International Conference on Machine Learning","author":"Maclaurin Dougal","year":"2015","unstructured":"Dougal Maclaurin, David Duvenaud, and Ryan P. Adams. 2015. Gradient-based hyperparameter optimization through reversible learning. In 32nd International Conference on Machine Learning. JMLR, 2113\u20132122."},{"key":"e_1_3_3_119_2","first-page":"20373","article-title":"Excess capacity and backdoor poisoning","volume":"34","author":"Manoj Naren","year":"2021","unstructured":"Naren Manoj and Avrim Blum. 2021. Excess capacity and backdoor poisoning. Adv Neural Inf Proc Syst. 34 (2021), 20373\u201320384.","journal-title":"Adv Neural Inf Proc Syst."},{"key":"e_1_3_3_120_2","article-title":"Preventing repeated real world AI failures by cataloging incidents: The AI incident database","author":"McGregor Sean","year":"2020","unstructured":"Sean McGregor. 2020. Preventing repeated real world AI failures by cataloging incidents: The AI incident database. arXiv:2011.08512 (2020).","journal-title":"arXiv:2011.08512"},{"key":"e_1_3_3_121_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01304"},{"key":"e_1_3_3_122_2","doi-asserted-by":"publisher","DOI":"10.5555\/2886521.2886721"},{"key":"e_1_3_3_123_2","article-title":"secml: A Python library for secure and explainable ML","author":"Melis Marco","year":"2019","unstructured":"Marco Melis, Ambra Demontis, Maura Pintor, Angelo Sotgiu, and Battista Biggio. 2019. secml: A Python library for secure and explainable ML. arXiv:1912.10013 (2019).","journal-title":"arXiv:1912.10013"},{"key":"e_1_3_3_124_2","first-page":"80","volume-title":"25th IEEE Pacific Rim International Symposium on Dependable Computing","author":"M\u00fcller Nicolas M.","year":"2020","unstructured":"Nicolas M. M\u00fcller, Daniel Kowatsch, and Konstantin B\u00f6ttinger. 2020. Data poisoning attacks on regression learning and corresponding defenses. In 25th IEEE Pacific Rim International Symposium on Dependable Computing. IEEE, 80\u201389."},{"key":"e_1_3_3_125_2","first-page":"27","volume-title":"10th ACM Workshop on Artificial Intelligence and Security","author":"Mu\u00f1oz-Gonz\u00e1lez Luis","year":"2017","unstructured":"Luis Mu\u00f1oz-Gonz\u00e1lez, Battista Biggio, Ambra Demontis, Andrea Paudice, Vasin Wongrassamee, Emil C. Lupu, and Fabio Roli. 2017. Towards poisoning of deep learning algorithms with back-gradient optimization. In 10th ACM Workshop on Artificial Intelligence and Security. ACM, 27\u201338."},{"key":"e_1_3_3_126_2","first-page":"17","volume-title":"ML in Cyber Trust","author":"Nelson Blaine","year":"2009","unstructured":"Blaine Nelson, Marco Barreno, Fuching Jack Chi, Anthony D. Joseph, Benjamin I. P. Rubinstein, Udam Saini, Charles Sutton, J. D. Tygar, and Kai Xia. 2009. Misleading learners: Co-opting your spam filter. In ML in Cyber Trust. Springer, 17\u201351."},{"key":"e_1_3_3_127_2","first-page":"1","volume-title":"USENIX Workshop on Large-Scale Exploits and Emergent Threats","author":"Nelson Blaine","year":"2008","unstructured":"Blaine Nelson, Marco Barreno, Fuching Jack Chi, Anthony D. Joseph, Benjamin I. P. Rubinstein, Udam Saini, Charles Sutton, J. Doug Tygar, and Kai Xia. 2008. Exploiting ML to subvert your spam filter. In USENIX Workshop on Large-Scale Exploits and Emergent Threats. USENIX, 1\u20139."},{"key":"e_1_3_3_128_2","doi-asserted-by":"publisher","DOI":"10.1007\/11856214_5"},{"key":"e_1_3_3_129_2","volume-title":"International Conference on Advances in Neural Information Processing Systems","author":"Nguyen Tuan Anh","year":"2020","unstructured":"Tuan Anh Nguyen and Anh Tran. 2020. Input-aware dynamic backdoor attack. In International Conference on Advances in Neural Information Processing Systems."},{"key":"e_1_3_3_130_2","volume-title":"International Conference on Learning Representations","author":"Nguyen Tuan Anh","year":"2021","unstructured":"Tuan Anh Nguyen and Anh Tuan Tran. 2021. WaNet\u2014Imperceptible warping-based backdoor attack. In International Conference on Learning Representations. OpenReview.net."},{"key":"e_1_3_3_131_2","article-title":"Adversarial robustness toolbox v1.2.0","volume":"1807","author":"Nicolae Maria-Irina","year":"2018","unstructured":"Maria-Irina Nicolae, Mathieu Sinn, Minh Ngoc Tran, Beat Buesser, Ambrish Rawat, Martin Wistuba, Valentina Zantedeschi, Nathalie Baracaldo, Bryant Chen, Heiko Ludwig, Ian Molloy, and Ben Edwards. 2018. Adversarial robustness toolbox v1.2.0. CoRR 1807.01069 (2018).","journal-title":"CoRR"},{"key":"e_1_3_3_132_2","article-title":"Transferability in ML: From phenomena to black-box attacks using adversarial samples","author":"Papernot Nicolas","year":"2016","unstructured":"Nicolas Papernot, Patrick McDaniel, and Ian Goodfellow. 2016. Transferability in ML: From phenomena to black-box attacks using adversarial samples. arXiv:1605.07277 (2016).","journal-title":"arXiv:1605.07277"},{"key":"e_1_3_3_133_2","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"e_1_3_3_134_2","first-page":"5","volume-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","author":"Paudice Andrea","year":"2018","unstructured":"Andrea Paudice, Luis Mu\u00f1oz-Gonz\u00e1lez, and Emil C. Lupu. 2018. Label sanitization against label flipping poisoning attacks. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 5\u201315."},{"key":"e_1_3_3_135_2","volume-title":"IEEE Symposium on Security and Privacy","author":"Perdisci R.","year":"2006","unstructured":"R. Perdisci, D. Dagon, Wenke Lee, P. Fogla, and M. Sharif. 2006. Misleading worm signature generators using deliberate noise injection. In IEEE Symposium on Security and Privacy."},{"key":"e_1_3_3_136_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66415-2_4"},{"key":"e_1_3_3_137_2","article-title":"Indicators of attack failure: Debugging and improving optimization of adversarial examples","author":"Pintor Maura","year":"2021","unstructured":"Maura Pintor, Luca Demetrio, Angelo Sotgiu, Giovanni Manca, Ambra Demontis, Nicholas Carlini, Battista Biggio, and Fabio Roli. 2021. Indicators of attack failure: Debugging and improving optimization of adversarial examples. arXiv preprint arXiv:2106.09947 (2021).","journal-title":"arXiv preprint arXiv:2106.09947"},{"key":"e_1_3_3_138_2","article-title":"ONION: A simple and effective defense against textual backdoor attacks","author":"Qi Fanchao","year":"2020","unstructured":"Fanchao Qi, Yangyi Chen, Mukai Li, Zhiyuan Liu, and Maosong Sun. 2020. ONION: A simple and effective defense against textual backdoor attacks. arXiv:2011.10369 (2020).","journal-title":"arXiv:2011.10369"},{"key":"e_1_3_3_139_2","first-page":"14004","volume-title":"International Conference on Advances in Neural Information Processing Systems","author":"Qiao Ximing","year":"2019","unstructured":"Ximing Qiao, Yukun Yang, and Hai Li. 2019. Defending neural backdoors via generative distribution modeling. In International Conference on Advances in Neural Information Processing Systems. 14004\u201314013."},{"key":"e_1_3_3_140_2","first-page":"7974","volume-title":"International Conference on Machine Learning","author":"Rakhsha Amin","year":"2020","unstructured":"Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, and Adish Singla. 2020. Policy teaching via environment poisoning: Training-time adversarial attacks against reinforcement learning. In International Conference on Machine Learning. PMLR, 7974\u20137984."},{"key":"e_1_3_3_141_2","first-page":"8230","volume-title":"International Conference on Machine Learning","author":"Rosenfeld Elan","year":"2020","unstructured":"Elan Rosenfeld, Ezra Winston, Pradeep Ravikumar, and Zico Kolter. 2020. Certified robustness to label-flipping attacks via randomized smoothing. In International Conference on Machine Learning. PMLR, 8230\u20138241."},{"key":"e_1_3_3_142_2","doi-asserted-by":"publisher","DOI":"10.1145\/1644893.1644895"},{"key":"e_1_3_3_143_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6871"},{"key":"e_1_3_3_144_2","article-title":"Dynamic backdoor attacks against ML models","author":"Salem Ahmed","year":"2020","unstructured":"Ahmed Salem, Rui Wen, Michael Backes, Shiqing Ma, and Yang Zhang. 2020. Dynamic backdoor attacks against ML models. arXiv (2020).","journal-title":"arXiv"},{"key":"e_1_3_3_145_2","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2020.2968275"},{"key":"e_1_3_3_146_2","unstructured":"Esha Sarkar Hadjer Benkraouda and Michail Maniatakos. 2020. FaceHack: Triggering backdoored facial recognition sys. using facial characteristics. arXive:2006.11623 (2020)."},{"key":"e_1_3_3_147_2","first-page":"9389","volume-title":"International Conference on Machine Learning","author":"Schwarzschild Avi","year":"2021","unstructured":"Avi Schwarzschild, Micah Goldblum, Arjun Gupta, John P. Dickerson, and Tom Goldstein. 2021. Just how toxic is data poisoning? A unified benchmark for backdoor and data poisoning attacks. In International Conference on Machine Learning. PMLR, 9389\u20139398."},{"key":"e_1_3_3_148_2","volume-title":"USENIX Security Symposium.","author":"Severi Giorgio","year":"2021","unstructured":"Giorgio Severi, Jim Meyer, Scott Coull, and Alina Oprea. 2021. Explanation-guided backdoor poisoning attacks against malware classifiers. In USENIX Security Symposium."},{"key":"e_1_3_3_149_2","first-page":"6106","volume-title":"International Conference on Advances in Neural Information Processing Systems","author":"Shafahi Ali","year":"2018","unstructured":"Ali Shafahi, W. Ronny Huang, Mahyar Najibi, Octavian Suciu, Christoph Studer, Tudor Dumitras, and Tom Goldstein. 2018. Poison frogs! Targeted clean-label poisoning attacks on neural networks. In International Conference on Advances in Neural Information Processing Systems. 6106\u20136116."},{"key":"e_1_3_3_150_2","volume-title":"USENIX Security Symposium.","author":"Shan Shawn","year":"2022","unstructured":"Shawn Shan, Arjun Nitin Bhagoji, Haitao Zheng, and Ben Y. Zhao. 2022. Traceback of targeted data poisoning attacks in neural networks. In USENIX Security Symposium.USENIX Association."},{"key":"e_1_3_3_151_2","volume-title":"IEEE Symposium on Security and Privacy","author":"Shejwalkar Virat","year":"2022","unstructured":"Virat Shejwalkar, Amir Houmansadr, Peter Kairouz, and Daniel Ramage. 2022. Back to the drawing board: A critical evaluation of poisoning attacks on federated learning. In IEEE Symposium on Security and Privacy."},{"key":"e_1_3_3_152_2","article-title":"Backdoor scanning for deep neural networks through k-arm optimization","author":"Shen Guangyu","year":"2021","unstructured":"Guangyu Shen, Yingqi Liu, Guanhong Tao, Shengwei An, Qiuling Xu, Siyuan Cheng, Shiqing Ma, and Xiangyu Zhang. 2021. Backdoor scanning for deep neural networks through k-arm optimization. arXiv:2102.05123 (2021).","journal-title":"arXiv:2102.05123"},{"key":"e_1_3_3_153_2","first-page":"175","volume-title":"IEEE European Symposium on Security and Privacy","author":"Shokri Reza","year":"2020","unstructured":"Reza Shokri et\u00a0al. 2020. Bypassing backdoor detection algorithms in deep learning. In IEEE European Symposium on Security and Privacy. IEEE, 175\u2013183."},{"key":"e_1_3_3_154_2","first-page":"162","volume-title":"European Conference on Machine Learning (ECML) and European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD)","author":"Solans David","year":"2020","unstructured":"David Solans, Battista Biggio, and Carlos Castillo. 2020. Poisoning attacks on algorithmic fairness. In European Conference on Machine Learning (ECML) and European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD). Springer, 162\u2013177."},{"key":"e_1_3_3_155_2","first-page":"305","volume-title":"IEEE Symposium on Security and Privacy","author":"Sommer Robin","year":"2010","unstructured":"Robin Sommer and Vern Paxson. 2010. Outside the closed world: On using ML for network intrusion detection. In IEEE Symposium on Security and Privacy. IEEE, 305\u2013316."},{"key":"e_1_3_3_156_2","article-title":"Exposing backdoors in robust ML models","author":"Soremekun Ezekiel","year":"2020","unstructured":"Ezekiel Soremekun, Sakshi Udeshi, Sudipta Chattopadhyay, and Andreas Zeller. 2020. Exposing backdoors in robust ML models. arXiv (2020).","journal-title":"arXiv"},{"key":"e_1_3_3_157_2","article-title":"Sleeper agent: Scalable hidden trigger backdoors for neural networks trained from scratch","author":"Souri Hossein","year":"2021","unstructured":"Hossein Souri, Micah Goldblum, Liam Fowl, Rama Chellappa, and Tom Goldstein. 2021. Sleeper agent: Scalable hidden trigger backdoors for neural networks trained from scratch. arXiv:2106.08970 (2021).","journal-title":"arXiv:2106.08970"},{"key":"e_1_3_3_158_2","first-page":"3517","volume-title":"International Conference on Neural Information Processing Systems","author":"Steinhardt Jacob","year":"2017","unstructured":"Jacob Steinhardt, Pang Wei Koh, and Percy Liang. 2017. Certified defenses for data poisoning attacks. In International Conference on Neural Information Processing Systems. 3517\u20133529."},{"key":"e_1_3_3_159_2","first-page":"1299","volume-title":"USENIX Security Symposium.","author":"Suciu Octavian","year":"2018","unstructured":"Octavian Suciu, Radu Marginean, Yigitcan Kaya, Hal Daume III, and Tudor Dumitras. 2018. When does ML FAIL? Generalized transferability for evasion and poisoning attacks. In USENIX Security Symposium.1299\u20131316."},{"key":"e_1_3_3_160_2","article-title":"Adversarial attack and defense on graph data: A survey","author":"Sun Lichao","year":"2018","unstructured":"Lichao Sun, Yingtong Dou, Carl Yang, Ji Wang, Philip S. Yu, Lifang He, and Bo Li. 2018. Adversarial attack and defense on graph data: A survey. arXiv:1812.10528 (2018).","journal-title":"arXiv:1812.10528"},{"key":"e_1_3_3_161_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00743"},{"key":"e_1_3_3_162_2","article-title":"Can you really backdoor federated learning?","author":"Sun Ziteng","year":"2019","unstructured":"Ziteng Sun, Peter Kairouz, Ananda Theertha Suresh, and H. Brendan McMahan. 2019. Can you really backdoor federated learning? arXiv (2019).","journal-title":"arXiv"},{"key":"e_1_3_3_163_2","first-page":"1","article-title":"On defending against label flipping attacks on malware detection system","author":"Taheri Rahim","year":"2020","unstructured":"Rahim Taheri, Reza Javidan, Mohammad Shojafar, Zahra Pooranian, Ali Miri, and Mauro Conti. 2020. On defending against label flipping attacks on malware detection system. Neural Comput. Applic. (2020), 1\u201320.","journal-title":"Neural Comput. Applic."},{"key":"e_1_3_3_164_2","unstructured":"Di Tang XiaoFeng Wang Haixu Tang and Kehuan Zhang. 2021. Demon in the variant: Statistical analysis of  \\(\\lbrace\\) DNNs \\(\\rbrace\\)  for robust backdoor contamination detection. (2021) 1541\u20131558."},{"key":"e_1_3_3_165_2","article-title":"A comprehensive survey on poisoning attacks and countermeasures in machine learning","author":"Tian Zhiyi","year":"2022","unstructured":"Zhiyi Tian, Lei Cui, Jie Liang, and Shui Yu. 2022. A comprehensive survey on poisoning attacks and countermeasures in machine learning. Comput. Surv. (2022).","journal-title":"Comput. Surv."},{"key":"e_1_3_3_166_2","first-page":"480","volume-title":"European Symposium on Research in Computer Security","author":"Tolpegin Vale","year":"2020","unstructured":"Vale Tolpegin, Stacey Truex, Mehmet Emre Gursoy, and Ling Liu. 2020. Data poisoning attacks against federated learning sytems. In European Symposium on Research in Computer Security. Springer, 480\u2013501."},{"key":"e_1_3_3_167_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"e_1_3_3_168_2","first-page":"601","volume-title":"USENIX Security Symposium.","author":"Tram\u00e8r Florian","year":"2016","unstructured":"Florian Tram\u00e8r, Fan Zhang, Ari Juels, Michael K. Reiter, and Thomas Ristenpart. 2016. Stealing ML models via prediction APIs. In USENIX Security Symposium.601\u2013618."},{"key":"e_1_3_3_169_2","first-page":"8011","volume-title":"Conference on Neural Information Processing Systems","author":"Tran Brandon","year":"2018","unstructured":"Brandon Tran, Jerry Li, and Aleksander M\u0105dry. 2018. Spectral signatures in backdoor attacks. In Conference on Neural Information Processing Systems. 8011\u20138021."},{"key":"e_1_3_3_170_2","article-title":"Label-consistent backdoor attacks","author":"Turner Alexander","year":"2019","unstructured":"Alexander Turner, Dimitris Tsipras, and Aleksander Madry. 2019. Label-consistent backdoor attacks. arXiv:1912.02771 (2019).","journal-title":"arXiv:1912.02771"},{"key":"e_1_3_3_171_2","article-title":"Model agnostic defence against backdoor attacks in ML","author":"Udeshi Sakshi","year":"2019","unstructured":"Sakshi Udeshi, Shanshan Peng, Gerald Woo, Lionell Loh, Louth Rawshan, and Sudipta Chattopadhyay. 2019. Model agnostic defence against backdoor attacks in ML. arXiv:1908.02203 (2019).","journal-title":"arXiv:1908.02203"},{"key":"e_1_3_3_172_2","first-page":"49","volume-title":"14th ACM Workshop on AI and Security","author":"Veldanda Akshaj Kumar","year":"2021","unstructured":"Akshaj Kumar Veldanda, Kang Liu, Benjamin Tan, Prashanth Krishnamurthy, Farshad Khorrami, Ramesh Karri, Brendan Dolan-Gavitt, and Siddharth Garg. 2021. NNoculation: Catching BadNets in the wild. In 14th ACM Workshop on AI and Security. 49\u201360."},{"key":"e_1_3_3_173_2","article-title":"ConFoc: Content-focus protection against trojan attacks on neural networks","author":"Villarreal-Vasquez Miguel","year":"2020","unstructured":"Miguel Villarreal-Vasquez and Bharat Bhargava. 2020. ConFoc: Content-focus protection against trojan attacks on neural networks. arXiv (2020).","journal-title":"arXiv"},{"key":"e_1_3_3_174_2","first-page":"707","volume-title":"IEEE Symposium on Security and Privacy, S&P","author":"Wang Bolun","year":"2019","unstructured":"Bolun Wang, Yuanshun Yao, Shawn Shan, Huiying Li, Bimal Viswanath, Haitao Zheng, and Ben Y Zhao. 2019. Neural cleanse: Identifying and mitigating backdoor attacks in neural networks. In IEEE Symposium on Security and Privacy, S&P. IEEE, 707\u2013723."},{"key":"e_1_3_3_175_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6086"},{"key":"e_1_3_3_176_2","first-page":"22769","volume-title":"International Conference on Machine Learning","author":"Wang Wenxiao","year":"2022","unstructured":"Wenxiao Wang, Alexander J. Levine, and Soheil Feizi. 2022. Improved certified defenses against data poisoning with (deterministic) finite aggregation. In International Conference on Machine Learning. PMLR, 22769\u201322783."},{"key":"e_1_3_3_177_2","article-title":"RAB: Provable robustness against backdoor attacks","author":"Weber Maurice","year":"2020","unstructured":"Maurice Weber, Xiaojun Xu, Bojan Karlas, Ce Zhang, and Bo Li. 2020. RAB: Provable robustness against backdoor attacks. arXiv:2003.08904 (2020).","journal-title":"arXiv:2003.08904"},{"key":"e_1_3_3_178_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3087332"},{"key":"e_1_3_3_179_2","article-title":"On the trade-off between adversarial and backdoor robustness","author":"Weng Cheng-Hsin","year":"2020","unstructured":"Cheng-Hsin Weng, Yan-Ting Lee, and Shan-Hung Brandon Wu. 2020. On the trade-off between adversarial and backdoor robustness. In International Conference on Neural Information Processing Systems.","journal-title":"International Conference on Neural Information Processing Systems"},{"key":"e_1_3_3_180_2","first-page":"6202","article-title":"Backdoor attacks against deep learning sys. in the physical world","author":"Wenger Emily","year":"2021","unstructured":"Emily Wenger, Josephine Passananti, Arjun Nitin Bhagoji, Yuanshun Yao, Haitao Zheng, and Ben Y. Zhao. 2021. Backdoor attacks against deep learning sys. in the physical world. In IEEE\/CVF International Conference on Computer Vision. 6202\u20136211.","journal-title":"IEEE\/CVF International Conference on Computer Vision"},{"key":"e_1_3_3_181_2","volume-title":"International Conference on Neural Information Processing Systems","author":"Wu Dongxian","year":"2021","unstructured":"Dongxian Wu and Yisen Wang. 2021. Adversarial neuron pruning purifies backdoored deep models. In International Conference on Neural Information Processing Systems."},{"key":"e_1_3_3_182_2","first-page":"1523","volume-title":"USENIX Security Symposium.","author":"Xi Zhaohan","year":"2021","unstructured":"Zhaohan Xi, Ren Pang, Shouling Ji, and Ting Wang. 2021. Graph backdoor. In USENIX Security Symposium.1523\u20131540."},{"key":"e_1_3_3_183_2","volume-title":"International Conference on Learning Representations","author":"Xiang Zhen","year":"2022","unstructured":"Zhen Xiang, David Miller, and George Kesidis. 2022. Post-training detection of backdoor attacks for two-class and multi-attack scenarios. In International Conference on Learning Representations."},{"key":"e_1_3_3_184_2","first-page":"1","volume-title":"IEEE 29th International Workshop on Machine Learning for Signal Processing","author":"Xiang Zhen","year":"2019","unstructured":"Zhen Xiang, David J. Miller, and George Kesidis. 2019. A benchmark study of backdoor data poisoning defenses for deep neural network classifiers and a novel defense. In IEEE 29th International Workshop on Machine Learning for Signal Processing. IEEE, 1\u20136."},{"key":"e_1_3_3_185_2","article-title":"Detection of backdoors in trained classifiers without access to the training set","author":"Xiang Zhen","year":"2020","unstructured":"Zhen Xiang, David J. Miller, and George Kesidis. 2020. Detection of backdoors in trained classifiers without access to the training set. IEEE Trans. Neural Netw. Learn. Syst. (2020).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"e_1_3_3_186_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414562"},{"key":"e_1_3_3_187_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2021.102280"},{"key":"e_1_3_3_188_2","article-title":"Characterizing attacks on deep reinforcement learning","author":"Xiao Chaowei","year":"2019","unstructured":"Chaowei Xiao, Xinlei Pan, Warren He, Jian Peng, Mingjie Sun, Jinfeng Yi, Mingyan Liu, Bo Li, and Dawn Song. 2019. Characterizing attacks on deep reinforcement learning. arXiv:1907.09470 (2019).","journal-title":"arXiv:1907.09470"},{"key":"e_1_3_3_189_2","first-page":"1689","volume-title":"32nd International Conference on Machine Learning","author":"Xiao Huang","year":"2015","unstructured":"Huang Xiao, Battista Biggio, Gavin Brown, Giorgio Fumera, Claudia Eckert, and Fabio Roli. 2015. Is feature selection secure against training data poisoning? In 32nd International Conference on Machine Learning. JMLR, 1689\u20131698."},{"key":"e_1_3_3_190_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.08.081"},{"key":"e_1_3_3_191_2","first-page":"870","volume-title":"20th European Conference on Artificial Intelligence. Including Prestigious Applications of AI","author":"Xiao Han","year":"2012","unstructured":"Han Xiao, Huang Xiao, and Claudia Eckert. 2012. Adversarial label flips attack on support vector machines. In 20th European Conference on Artificial Intelligence. Including Prestigious Applications of AI. IOS Press, 870\u2013875."},{"key":"e_1_3_3_192_2","volume-title":"International Conference on Learning Representations","author":"Xie Chulin","year":"2020","unstructured":"Chulin Xie, Keli Huang, Pin-Yu Chen, and Bo Li. 2020. DBA: Distributed backdoor attacks against federated learning. In International Conference on Learning Representations. OpenReview."},{"key":"e_1_3_3_193_2","doi-asserted-by":"publisher","DOI":"10.5555\/3463952.3464113"},{"key":"e_1_3_3_194_2","first-page":"103","volume-title":"IEEE Symposium on Security and Privacy","author":"Xu Xiaojun","year":"2021","unstructured":"Xiaojun Xu, Qi Wang, Huichen Li, Nikita Borisov, Carl A. Gunter, and Bo Li. 2021. Detecting AI trojans using meta neural analysis. In IEEE Symposium on Security and Privacy. IEEE, 103\u2013120."},{"key":"e_1_3_3_195_2","article-title":"Generative poisoning attack method against neural networks","volume":"1703","author":"Yang Chaofei","year":"2017","unstructured":"Chaofei Yang, Qing Wu, Hai Li, and Yiran Chen. 2017. Generative poisoning attack method against neural networks. CoRR abs\/1703.01340 (2017).","journal-title":"CoRR"},{"key":"e_1_3_3_196_2","first-page":"25154","volume-title":"International Conference on Machine Learning","author":"Yang Yu","year":"2022","unstructured":"Yu Yang, Tian Yu Liu, and Baharan Mirzasoleiman. 2022. Not All poisons are created equal: Robust training against data poisoning. In International Conference on Machine Learning. PMLR, 25154\u201325165."},{"key":"e_1_3_3_197_2","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3354209"},{"key":"e_1_3_3_198_2","first-page":"117","volume-title":"13th ACM Workshop on AI and Security","author":"Yoshida Kota","year":"2020","unstructured":"Kota Yoshida and Takeshi Fujino. 2020. Disabling backdoor and identifying poison data by using knowledge distillation in backdoor attacks on deep neural networks. In 13th ACM Workshop on AI and Security. 117\u2013127."},{"key":"e_1_3_3_199_2","first-page":"1","volume-title":"Workshop on Machine Learning in High-performance Computing Environments","author":"Young Steven R.","year":"2015","unstructured":"Steven R. Young, Derek C. Rose, Thomas P. Karnowski, Seung-Hwan Lim, and Robert M. Patton. 2015. Optimizing deep learning hyper-parameters through an evolutionary algorithm. In Workshop on Machine Learning in High-performance Computing Environments. 1\u20135."},{"key":"e_1_3_3_200_2","volume-title":"International Conference on Learning Representations","author":"Zeng Yi","year":"2022","unstructured":"Yi Zeng, Si Chen, Won Park, Zhuoqing Mao, Ming Jin, and Ruoxi Jia. 2022. Adversarial unlearning of backdoors via implicit hypergradient. In International Conference on Learning Representations."},{"key":"e_1_3_3_201_2","article-title":"DeepSweep: An evaluation framework for mitigating DNN backdoor attacks using data augmentation","author":"Zeng Yi","year":"2020","unstructured":"Yi Zeng, Han Qiu, Shangwei Guo, Tianwei Zhang, Meikang Qiu, and Bhavani Thuraisingham. 2020. DeepSweep: An evaluation framework for mitigating DNN backdoor attacks using data augmentation. arXiv:2012.07006 (2020).","journal-title":"arXiv:2012.07006"},{"key":"e_1_3_3_202_2","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom\/BigDataSE.2019.00057"},{"key":"e_1_3_3_203_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-9739-8_7"},{"key":"e_1_3_3_204_2","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2017.7926118"},{"key":"e_1_3_3_205_2","article-title":"TAD: Trigger approximation based black-box trojan detection for AI","author":"Zhang Xinqiao","year":"2021","unstructured":"Xinqiao Zhang, Huili Chen, and Farinaz Koushanfar. 2021. TAD: Trigger approximation based black-box trojan detection for AI. arXiv (2021).","journal-title":"arXiv"},{"key":"e_1_3_3_206_2","first-page":"11225","volume-title":"International Conference on Machine Learning","author":"Zhang Xuezhou","year":"2020","unstructured":"Xuezhou Zhang, Yuzhe Ma, Adish Singla, and Xiaojin Zhu. 2020. Adaptive reward-poisoning attacks against reinforcement learning. In International Conference on Machine Learning. PMLR, 11225\u201311234."},{"key":"e_1_3_3_207_2","article-title":"Trojaning language models for fun and profit","volume":"2008","author":"Zhang Xinyang","year":"2020","unstructured":"Xinyang Zhang, Zheng Zhang, and Ting Wang. 2020. Trojaning language models for fun and profit. CoRR abs\/2008.00312 (2020).","journal-title":"CoRR"},{"key":"e_1_3_3_208_2","first-page":"15","volume-title":"26th ACM Symposium on Access Control Models and Technologies","author":"Zhang Zaixi","year":"2021","unstructured":"Zaixi Zhang, Jinyuan Jia, Binghui Wang, and Neil Zhenqiang Gong. 2021. Backdoor attacks to graph neural networks. In 26th ACM Symposium on Access Control Models and Technologies. ACM, 15\u201326."},{"key":"e_1_3_3_209_2","volume-title":"International Conference on Learning Representations","author":"Zhao Pu","year":"2020","unstructured":"Pu Zhao, Pin-Yu Chen, Payel Das, Karthikeyan Natesan Ramamurthy, and Xue Lin. 2020. Bridging mode connectivity in loss landscapes and adversarial robustness. In International Conference on Learning Representations."},{"key":"e_1_3_3_210_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01445"},{"key":"e_1_3_3_211_2","first-page":"595","volume-title":"International Conference on Algorithms and Architectures for Parallel Processing","author":"Zhao Ying","year":"2019","unstructured":"Ying Zhao, Junjun Chen, Jiale Zhang, Di Wu, Jian Teng, and Shui Yu. 2019. PDGAN: A novel poisoning defense method in federated learning using generative adversarial network. In International Conference on Algorithms and Architectures for Parallel Processing. Springer, 595\u2013609."},{"key":"e_1_3_3_212_2","doi-asserted-by":"publisher","DOI":"10.1145\/3374664.3375751"},{"key":"e_1_3_3_213_2","first-page":"7614","volume-title":"36th International Conference on Machine Learning","author":"Zhu Chen","year":"2019","unstructured":"Chen Zhu, W. Ronny Huang, Hengduo Li, Gavin Taylor, Christoph Studer, and Tom Goldstein. 2019. Transferable clean-label poisoning attacks on deep neural nets. In 36th International Conference on Machine Learning. PMLR, 7614\u20137623."},{"key":"e_1_3_3_214_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413546"},{"key":"e_1_3_3_215_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01614"},{"key":"e_1_3_3_216_2","volume-title":"International Conference on Learning Representations","author":"Z\u00fcgner Daniel","year":"2019","unstructured":"Daniel Z\u00fcgner and Stephan G\u00fcnnemann. 2019. Adversarial attacks on graph neural networks via meta learning. In International Conference on Learning Representations. OpenReview.net."}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3585385","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3585385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T12:37:56Z","timestamp":1750163876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3585385"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,13]]},"references-count":215,"journal-issue":{"issue":"13s","published-print":{"date-parts":[[2023,12,31]]}},"alternative-id":["10.1145\/3585385"],"URL":"https:\/\/doi.org\/10.1145\/3585385","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,13]]},"assertion":[{"value":"2022-05-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-21","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}