{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T03:19:32Z","timestamp":1725679172146},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,7,9]],"date-time":"2023-07-09T00:00:00Z","timestamp":1688860800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,9]],"date-time":"2023-07-09T00:00:00Z","timestamp":1688860800000},"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":[[2023,7,9]]},"DOI":"10.1109\/dac56929.2023.10247930","type":"proceedings-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T17:31:31Z","timestamp":1694799091000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Fast Adversarial Training with Dynamic Batch-level Attack Control"],"prefix":"10.1109","author":[{"given":"Jaewon","family":"Jung","sequence":"first","affiliation":[{"name":"College of Computing, Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaeyong","family":"Song","sequence":"additional","affiliation":[{"name":"College of Computing, Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongsun","family":"Jang","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyeyoon","family":"Lee","sequence":"additional","affiliation":[{"name":"College of Computing, Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kanghyun","family":"Choi","sequence":"additional","affiliation":[{"name":"College of Computing, Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noseong","family":"Park","sequence":"additional","affiliation":[{"name":"College of Computing, Yonsei University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinho","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Electrical and Computer Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17278"},{"article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","year":"2017","author":"goyal","key":"ref12"},{"key":"ref15","article-title":"Improving robustness using generated data","author":"gowal","year":"2021","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Adversarially robust generalization requires more data","author":"schmidt","year":"2018","journal-title":"NeurIPS"},{"key":"ref11","article-title":"On the loss landscape of adversarial training: Identifying challenges and how to overcome them","author":"liu","year":"2020","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Efficient adversarial training with transferable adversarial examples","author":"zheng","year":"2019","journal-title":"CVPR"},{"key":"ref2","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","author":"keskar","year":"2017","journal-title":"ICLRE"},{"key":"ref16","article-title":"Robust learning meets generative models: Can proxy distributions improve adversarial robustness?","author":"sehwag","year":"2021","journal-title":"ICLRE"},{"key":"ref19","article-title":"A closer look at deep learning heuristics: Learning rate restarts, warmup and distillation","author":"gotmare","year":"2019","journal-title":"ICLRE"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref24","article-title":"Averaging weights leads to wider optima and better generalization","author":"izmailov","year":"2018","journal-title":"UAI"},{"key":"ref23","article-title":"Wide residual networks","author":"zagoruyko","year":"2016","journal-title":"BMVC"},{"article-title":"Transferability in machine learning: From phenomena to black-box attacks using adversarial samples","year":"2016","author":"nicolas papernot","key":"ref26"},{"key":"ref25","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"foret","year":"2020","journal-title":"ICLRE"},{"key":"ref20","article-title":"Parametric noise injection: Trainable randomness to improve deep neural network robustness against adversarial attack","author":"rakin","year":"2019","journal-title":"CVPR"},{"key":"ref22","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Tech Rep"},{"key":"ref21","article-title":"Adversarial weight perturbation helps robust generalization","author":"wu","year":"2020","journal-title":"NeurIPS"},{"key":"ref8","article-title":"Adversarial training for free!","author":"shafahi","year":"2019","journal-title":"NeurIPS"},{"key":"ref7","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"2018","journal-title":"ICLRE"},{"key":"ref9","article-title":"Fast is better than free: Revisiting adversarial training","author":"wong","year":"2020","journal-title":"ICLRE"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00348"},{"key":"ref3","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"ICLRE"},{"key":"ref6","article-title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","author":"croce","year":"2020","journal-title":"ICML"},{"key":"ref5","article-title":"Rethinking softmax cross-entropy loss for adversarial robustness","author":"pang","year":"2020","journal-title":"ICLRE"}],"event":{"name":"2023 60th ACM\/IEEE Design Automation Conference (DAC)","start":{"date-parts":[[2023,7,9]]},"location":"San Francisco, CA, USA","end":{"date-parts":[[2023,7,13]]}},"container-title":["2023 60th ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10247654\/10247655\/10247930.pdf?arnumber=10247930","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T17:42:07Z","timestamp":1696268527000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10247930\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,9]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/dac56929.2023.10247930","relation":{},"subject":[],"published":{"date-parts":[[2023,7,9]]}}}