{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T16:29:11Z","timestamp":1771518551284,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076251"],"award-info":[{"award-number":["62076251"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,4]]},"DOI":"10.1145\/3627106.3627178","type":"proceedings-article","created":{"date-parts":[[2023,12,2]],"date-time":"2023-12-02T18:13:22Z","timestamp":1701540802000},"page":"580-593","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["PSP-Mal: Evading Malware Detection via Prioritized Experience-based Reinforcement Learning with Shapley Prior"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2766-3405","authenticated-orcid":false,"given":"Dazhi","family":"Zhan","sequence":"first","affiliation":[{"name":"Army Engineering University of PLA, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9738-0112","authenticated-orcid":false,"given":"Wei","family":"Bai","sequence":"additional","affiliation":[{"name":"Army Engineering University of PLA, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3051-4793","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"Army Engineering University of PLA, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8115-7020","authenticated-orcid":false,"given":"Yue","family":"Hu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8746-1106","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Academy of Military Sciences, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9678-6632","authenticated-orcid":false,"given":"Shize","family":"Guo","sequence":"additional","affiliation":[{"name":"Army Engineering University of PLA, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8615-7313","authenticated-orcid":false,"given":"Zhisong","family":"Pan","sequence":"additional","affiliation":[{"name":"Army Engineering University of PLA, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"e_1_3_2_1_2_1","volume-title":"Evading machine learning malware detection. Black Hat 2017","author":"Anderson S","year":"2017","unstructured":"Hyrum\u00a0S Anderson, Anant Kharkar, Bobby Filar, and Phil Roth. 2017. Evading machine learning malware detection. Black Hat 2017 (2017)."},{"key":"e_1_3_2_1_3_1","volume-title":"Ember: an open dataset for training static pe malware machine learning models. arXiv preprint arXiv:1804.04637","author":"Anderson S","year":"2018","unstructured":"Hyrum\u00a0S Anderson and Phil Roth. 2018. Ember: an open dataset for training static pe malware machine learning models. arXiv preprint arXiv:1804.04637 (2018)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IKT.2013.6620049"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"e_1_3_2_1_6_1","volume-title":"An empirical evaluation of thompson sampling. Advances in Neural Information Processing Systems 24","author":"Chapelle Olivier","year":"2011","unstructured":"Olivier Chapelle and Lihong Li. 2011. An empirical evaluation of thompson sampling. Advances in Neural Information Processing Systems 24 (2011)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2913439"},{"key":"e_1_3_2_1_8_1","volume-title":"Journal of Physics: Conference Series, Vol.\u00a01575","author":"Chen Jun","year":"2011","unstructured":"Jun Chen, Jingfei Jiang, Rongchun Li, and Yong Dou. 2020. Generating adversarial examples for static PE malware detector based on deep reinforcement learning. In Journal of Physics: Conference Series, Vol.\u00a01575. IOP Publishing, 012011."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638293"},{"key":"e_1_3_2_1_10_1","volume-title":"Italian Conference on Cybersecurity","author":"Demetrio Luca","year":"2019","unstructured":"Luca Demetrio, Battista Biggio, Giovanni Lagorio, Fabio Roli, and Alessandro Armando. 2019. Explaining vulnerabilities of deep learning to adversarial malware binaries. Italian Conference on Cybersecurity (2019)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3082330"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3473039"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3320269.3384733"},{"key":"e_1_3_2_1_14_1","volume-title":"Binary Black-Box Attacks Against Static Malware Detectors with Reinforcement Learning in Discrete Action Spaces. In IEEE Security and Privacy Workshops (SPW). IEEE, 85\u201391","author":"Ebrahimi Mohammadreza","year":"2021","unstructured":"Mohammadreza Ebrahimi, Jason Pacheco, Weifeng Li, James\u00a0Lee Hu, and Hsinchun Chen. 2021. Binary Black-Box Attacks Against Static Malware Detectors with Reinforcement Learning in Discrete Action Spaces. In IEEE Security and Privacy Workshops (SPW). IEEE, 85\u201391."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0231626"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107505"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2908033"},{"key":"e_1_3_2_1_18_1","volume-title":"Greedy function approximation: a gradient boosting machine. Annals of Statistics","author":"Friedman H","year":"2001","unstructured":"Jerome\u00a0H Friedman. 2001. Greedy function approximation: a gradient boosting machine. Annals of Statistics (2001), 1189\u20131232."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2021.102543"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11409"},{"key":"e_1_3_2_1_21_1","volume-title":"Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572","author":"Goodfellow J","year":"2014","unstructured":"Ian\u00a0J Goodfellow, Jonathon Shlens, and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)."},{"key":"e_1_3_2_1_22_1","volume-title":"SOREL-20M: A large scale benchmark dataset for malicious PE detection. arXiv preprint arXiv:2012.07634","author":"Harang Richard","year":"2020","unstructured":"Richard Harang and Ethan\u00a0M Rudd. 2020. SOREL-20M: A large scale benchmark dataset for malicious PE detection. arXiv preprint arXiv:2012.07634 (2020)."},{"key":"e_1_3_2_1_23_1","volume-title":"Black-box attacks against RNN based malware detection algorithms. arXiv preprint arXiv:1705.08131","author":"Hu Weiwei","year":"2017","unstructured":"Weiwei Hu and Ying Tan. 2017. Black-box attacks against RNN based malware detection algorithms. arXiv preprint arXiv:1705.08131 (2017)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIC.2019.8669079"},{"key":"e_1_3_2_1_25_1","volume-title":"Lightgbm: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems 30","author":"Ke Guolin","year":"2017","unstructured":"Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_26_1","volume-title":"COPYCAT: practical adversarial attacks on visualization-based malware detection. arXiv preprint arXiv:1909.09735","author":"Khormali Aminollah","year":"2019","unstructured":"Aminollah Khormali, Ahmed Abusnaina, Songqing Chen, DaeHun Nyang, and Aziz Mohaisen. 2019. COPYCAT: practical adversarial attacks on visualization-based malware detection. arXiv preprint arXiv:1909.09735 (2019)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553214"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014105"},{"key":"e_1_3_2_1_29_1","volume-title":"Deceiving end-to-end deep learning malware detectors using adversarial examples. arXiv preprint arXiv:1802.04528","author":"Kreuk Felix","year":"2018","unstructured":"Felix Kreuk, Assi Barak, and Aviv-Reuven. 2018. Deceiving end-to-end deep learning malware detectors using adversarial examples. arXiv preprint arXiv:1802.04528 (2018)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86514-6_3"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2020.102118"},{"key":"e_1_3_2_1_32_1","volume-title":"From local explanations to global understanding with explainable AI for trees. Nature machine intelligence 2, 1","author":"Lundberg M","year":"2020","unstructured":"Scott\u00a0M Lundberg, Gabriel Erion, Hugh Chen, Alex DeGrave, Jordan\u00a0M Prutkin, Bala Nair, Ronit Katz, Jonathan Himmelfarb, Nisha Bansal, and Su-In Lee. 2020. From local explanations to global understanding with explainable AI for trees. Nature machine intelligence 2, 1 (2020), 56\u201367."},{"key":"e_1_3_2_1_33_1","volume-title":"A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems 30","author":"Lundberg M","year":"2017","unstructured":"Scott\u00a0M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_34_1","unstructured":"Christoph Molnar. 2020. Interpretable machine learning. Lulu. com."},{"key":"e_1_3_2_1_35_1","volume-title":"International Conference on Machine Learning, Vol.\u00a01. 2.","author":"Ng Y","year":"2000","unstructured":"Andrew\u00a0Y Ng, Stuart Russell, 2000. Algorithms for inverse reinforcement learning.. In International Conference on Machine Learning, Vol.\u00a01. 2."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00073"},{"key":"e_1_3_2_1_37_1","volume-title":"MERLIN\u2013Malware Evasion with Reinforcement LearnINg. arXiv preprint arXiv:2203.12980","author":"Quertier Tony","year":"2022","unstructured":"Tony Quertier, Benjamin Marais, St\u00e9phane Morucci, and Bertrand Fournel. 2022. MERLIN\u2013Malware Evasion with Reinforcement LearnINg. arXiv preprint arXiv:2203.12980 (2022)."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence.","author":"Raff Edward","year":"2018","unstructured":"Edward Raff, Jon Barker, Jared Sylvester, Robert Brandon, Bryan Catanzaro, and Charles\u00a0K Nicholas. 2018. Malware detection by eating a whole exe. In Proceedings of the AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00470-5_23"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-70500-0_25"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/MALWARE.2015.7413680"},{"key":"e_1_3_2_1_42_1","volume-title":"Prioritized experience replay. arXiv preprint arXiv:1511.05952","author":"Schaul Tom","year":"2015","unstructured":"Tom Schaul, John Quan, Ioannis Antonoglou, and David Silver. 2015. Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)."},{"key":"e_1_3_2_1_43_1","volume-title":"USENIX Security Symposium. 1487\u20131504","author":"Severi Giorgio","year":"2021","unstructured":"Giorgio Severi, Jim Meyer, Scott\u00a0E Coull, and Alina Oprea. 2021. Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers.. In USENIX Security Symposium. 1487\u20131504."},{"key":"e_1_3_2_1_44_1","volume-title":"Mab-malware: A reinforcement learning framework for attacking static malware classifiers. arXiv preprint arXiv:2003.03100","author":"Song Wei","year":"2020","unstructured":"Wei Song, Xuezixiang Li, Sadia Afroz, Deepali Garg, Dmitry Kuznetsov, and Heng Yin. 2020. Mab-malware: A reinforcement learning framework for attacking static malware classifiers. arXiv preprint arXiv:2003.03100 (2020)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2019.00015"},{"key":"e_1_3_2_1_46_1","volume-title":"Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199","author":"Szegedy Christian","year":"2013","unstructured":"Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEC48606.2020.9185810"},{"key":"e_1_3_2_1_49_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Wang Ziyu","year":"2016","unstructured":"Ziyu Wang, Tom Schaul, Matteo Hessel, Hado Hasselt, Marc Lanctot, and Nando Freitas. 2016. Dueling network architectures for deep reinforcement learning. In International Conference on Machine Learning. PMLR, 1995\u20132003."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3290480.3290494"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761337"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/BWCCA.2010.85"},{"key":"e_1_3_2_1_53_1","volume-title":"the European Conference on Artificial Intelligence. IOS Press, 2536\u20132542","author":"Yuan Junkun","year":"2020","unstructured":"Junkun Yuan, Shaofang Zhou, Lanfen Lin, Feng Wang, and Jia Cui. 2020. Black-box adversarial attacks against deep learning based malware binaries detection with GAN. In the European Conference on Artificial Intelligence. IOS Press, 2536\u20132542."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2023.103103"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3153844"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2022.102869"}],"event":{"name":"ACSAC '23: Annual Computer Security Applications Conference","location":"Austin TX USA","acronym":"ACSAC '23"},"container-title":["Annual Computer Security Applications Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627106.3627178","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627106.3627178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:39:28Z","timestamp":1755884368000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627106.3627178"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":56,"alternative-id":["10.1145\/3627106.3627178","10.1145\/3627106"],"URL":"https:\/\/doi.org\/10.1145\/3627106.3627178","relation":{},"subject":[],"published":{"date-parts":[[2023,12,4]]},"assertion":[{"value":"2023-12-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}