{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:37:30Z","timestamp":1730299050901,"version":"3.28.0"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,5]],"date-time":"2023-12-05T00:00:00Z","timestamp":1701734400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,5]]},"DOI":"10.1109\/ssci52147.2023.10371946","type":"proceedings-article","created":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T14:30:22Z","timestamp":1704119422000},"page":"671-676","source":"Crossref","is-referenced-by-count":1,"title":["Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidence"],"prefix":"10.1109","author":[{"given":"Svetlana","family":"Pavlitska","sequence":"first","affiliation":[{"name":"FZI Research Center for Information Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hannes","family":"Grolig","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology (KIT),Karlsruhe,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J. Marius","family":"Zollner","sequence":"additional","affiliation":[{"name":"FZI Research Center for Information Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Explaining and harnessing adversarial examples","volume-title":"International Conference on Learning Repre-sentations (ICLR)","author":"Goodfellow","key":"ref1"},{"article-title":"Intriguing properties of neural networks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Szegedy","key":"ref2"},{"key":"ref3","article-title":"Adversarial training for free!","author":"Shafahi","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"article-title":"Bag of Tricks for Adversarial Training","volume-title":"International Conference on Learning Representations (ICLR)","author":"Pang","key":"ref4"},{"article-title":"Adversarial robustness against the union of multiple perturbation models","volume-title":"International Conference on Machine Learning (ICML)","author":"Maini","key":"ref5"},{"article-title":"Towards the first adversarially robust neural network model on mnist","volume-title":"International Conference on Learning Representations (ICLR)","author":"Schott","key":"ref6"},{"article-title":"Synthesizing Ro-bust Adversarial Examples","volume-title":"International Conference on Machine Learning (ICML)","author":"Athalye","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref9","article-title":"Do adversarially robust imagenet models transfer better?","author":"Salman","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NIPS)s"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00090"},{"key":"ref11","article-title":"Understanding and improving fast adversarial training","author":"Andriushchenko","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"article-title":"Overfitting in adversarially robust deep learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Rice","key":"ref13"},{"volume-title":"Pruning filters for efficient convnets","year":"2017","author":"Li","key":"ref14"},{"volume-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","year":"2016","author":"Han","key":"ref15"},{"article-title":"And the bit goes down: Revisiting the quantization of neural networks","volume-title":"International Conference on Learning Representations (ICLR). Open-Review. net","author":"Stock","key":"ref16"},{"article-title":"Attacking binarized neural networks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Galloway","key":"ref17"},{"key":"ref18","article-title":"Defend deep neural networks against adversarial examples via fixed and dynamic quantized activation functions","author":"Rakin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/BIGCOMP.2019.8679132"},{"article-title":"Defensive quantization: When efficiency meets robustness","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lin","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"volume-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref28","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","volume":"absI1704.04861","author":"Howard","year":"2017","journal-title":"CoRR"},{"article-title":"Incremental network quantization: Towards lossless cnns with low-precision weights","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhou","key":"ref29"},{"key":"ref30","article-title":"Dynamic network surgery for efficient dnns","author":"Guo","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"International Conference on Learning Representations (ICLR)","author":"Simonyan","key":"ref32"},{"volume-title":"Reading digits in natural images with unsupervised feature learning","year":"2011","author":"Netzer","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2018.23198"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3453688.3461755"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01233-4_15"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3568160.3570230"},{"key":"ref40","article-title":"Adversarial robustness of pruned neural networks","author":"Wang","year":"2018","journal-title":"Preprint"},{"key":"ref41","article-title":"Sparse dnns with improved adversarial robustness","volume":"31","author":"Guo","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref42","article-title":"Structured bayesian pruning via log-normal multiplicative noise","volume":"30","author":"Neklyudov","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00007"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref47","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00612"},{"key":"ref49","first-page":"9356","article-title":"Dropnet: reducing neural network complexity via iterative pruning","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Min"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00153"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.03.108"},{"article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hendrycks","key":"ref53"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06049-9"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref56","article-title":"Model com-pression with adversarial robustness: A unified optimization framework","author":"Gui","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref57","article-title":"Certifying some distributional robustness with principled adversarial training","volume-title":"International Conference on Learning Representations (ICLR). OpenReview.net","author":"Sinha","year":"2018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00020"},{"key":"ref59","article-title":"Learning both weights and con-nections for efficient neural network","volume":"28","author":"Han","year":"2015","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref60","article-title":"Hydra: Pruning adversari-ally robust neural networks","author":"Sehwag","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"article-title":"Triple wins: Boosting accuracy, robustness and efficiency together by enabling input-adaptive inference","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hu","key":"ref61"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_19"},{"article-title":"Evaluating the robustness of neural networks: An extreme value theory approach","volume-title":"International Conference on Learning Representations (ICLR)","author":"Weng","key":"ref63"},{"key":"ref64","article-title":"Unlabeled data improves adversarial robustness","volume":"32","author":"Carmon","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref65","article-title":"Shallow-deep networks: Under-standing and mitigating network overthinking","volume-title":"International Conference on Machine Learning (ICML)","author":"Kaya","year":"2019"},{"article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Frankle","key":"ref66"},{"article-title":"Rethinking the value of network pruning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Liu","key":"ref67"}],"event":{"name":"2023 IEEE Symposium Series on Computational Intelligence (SSCI)","start":{"date-parts":[[2023,12,5]]},"location":"Mexico City, Mexico","end":{"date-parts":[[2023,12,8]]}},"container-title":["2023 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10371778\/10371788\/10371946.pdf?arnumber=10371946","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T17:11:10Z","timestamp":1705079470000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10371946\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,5]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/ssci52147.2023.10371946","relation":{},"subject":[],"published":{"date-parts":[[2023,12,5]]}}}