{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:24:13Z","timestamp":1761582253802,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"AI2050 Program at Schmidt Futures","award":["G-22-63172"],"award-info":[{"award-number":["G-22-63172"]}]},{"name":"Capgemini SE","award":["ERC-2020-AdG","101020093"],"award-info":[{"award-number":["ERC-2020-AdG","101020093"]}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JP Morgan Graduate Fellowships"},{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]},{"name":"United States Air Force Artificial Intelligence Accelerator","award":["FA8750-19-2-1000"],"award-info":[{"award-number":["FA8750-19-2-1000"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/lra.2023.3240930","type":"journal-article","created":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T18:45:51Z","timestamp":1675190751000},"page":"1595-1602","source":"Crossref","is-referenced-by-count":7,"title":["Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6117-0076","authenticated-orcid":false,"given":"Mathias","family":"Lechner","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9673-1267","authenticated-orcid":false,"given":"Alexander","family":"Amini","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5473-3566","authenticated-orcid":false,"given":"Daniela","family":"Rus","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology, Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2985-7724","authenticated-orcid":false,"given":"Thomas A.","family":"Henzinger","sequence":"additional","affiliation":[{"name":"Institute of Science and Technology Austria (ISTA), Klosterneuburg, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Intriguing properties of neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Szegedy","year":"2014"},{"key":"ref2","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2307\/1969022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"ref5","first-page":"12","article-title":"Robot learning from demonstration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Atkeson","year":"1997"},{"key":"ref6","first-page":"1485","article-title":"Robustness and regularization of support vector machines","volume":"10","author":"Xu","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.06083"},{"key":"ref8","article-title":"Improving the generalization of adversarial training with domain adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2019"},{"key":"ref9","first-page":"4582","article-title":"Poisoning attacks against support vector machines","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Biggio","year":"2012"},{"key":"ref10","first-page":"3488","article-title":"Robust learning from untrusted sources","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Konstantinov","year":"2019"},{"key":"ref11","article-title":"Adversarial training can hurt generalization","volume-title":"CoRR","volume":"abs\/1906.06032","author":"Raghunathan"},{"key":"ref12","first-page":"944","article-title":"Efficient neural network robustness certification with general activation functions","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Zhang","year":"2018"},{"key":"ref13","article-title":"Robustness may be at odds with accuracy","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tsipras","year":"2018"},{"key":"ref14","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561036"},{"key":"ref17","first-page":"29935","article-title":"Data augmentation can improve robustness","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Rebuffi","year":"2021"},{"key":"ref18","first-page":"804","article-title":"A law of robustness for two-layers neural networks","volume-title":"Proc. Conf. Learn. Theory","author":"Bubeck","year":"2021"},{"key":"ref19","first-page":"27378","article-title":"Understanding the robustness in vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01611"},{"key":"ref21","first-page":"2021","article-title":"Bag of tricks for adversarial training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pang"},{"key":"ref22","first-page":"2958","article-title":"Adversarial weight perturbation helps robust generalization","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Wu","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3578580"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20103"},{"key":"ref25","article-title":"Adversarial patch","volume-title":"Proc. NeurIPS Mach. Learn. Comput. Secur. Workshop","author":"Brown","year":"2017"},{"key":"ref26","first-page":"5025","article-title":"Adversarial risk and the dangers of evaluating against weak attacks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Uesato","year":"2018"},{"key":"ref27","article-title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Athalye","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23288"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-45237-7_5"},{"key":"ref30","first-page":"26831","article-title":"Are transformers more robust than CNNs","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Bai","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63387-9_5"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-89716-1_10"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16496"},{"key":"ref34","article-title":"Adversarial machine learning at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kurakin","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref37","first-page":"3353","article-title":"Adversarial training for free!","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Shafahi","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.07.012"},{"key":"ref39","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref40","first-page":"3240","article-title":"Neural Lyapunov control","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Chang","year":"2019"},{"key":"ref41","first-page":"5998","article-title":"Infinite time horizon safety of Bayesian neural networks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Lechner","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20695"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01306"},{"key":"ref44","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968306"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref47","article-title":"Searching for activation functions","volume-title":"Proc. Int. Conf. Learn. Representations, Workshop Track","author":"Ramachandran","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812276"},{"key":"ref49","article-title":"Attention is all you need","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref50","first-page":"23296","article-title":"Intriguing properties of vision transformers","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Naseer","year":"2021"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58558-7_29"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00494"},{"key":"ref55","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clevert","year":"2016"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/10024862\/10032803-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/10024862\/10032803.pdf?arnumber=10032803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T10:18:08Z","timestamp":1707819488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10032803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":55,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lra.2023.3240930","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}