{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T16:40:35Z","timestamp":1788280835026,"version":"build-2803163510"},"reference-count":40,"publisher":"World Scientific Pub Co Pte Ltd","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["World Sci. Ann. Rev. Artif. Intell."],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p> Adversarial examples (AEs) are malicious test-data samples (typically images) generated by applying carefully calculated perturbations to clean samples. The added perturbations are usually human-imperceptible but the AEs can fool a machine learning (ML) model to make misclassifications. Although multiple methods were proposed to generate AEs, the ability to generalize is very limited; that is, they easily overfit to their source, single, white-box ML models and the generated AEs rarely work for other models. In this paper, we propose a black-box attack approach that crafts transferable AEs that can attack a wide range of ML models without knowing those model details. Our novel method consists of an elastic momentum (EM) that expedites gradient descent to avoid early overfitting, and a random erasure (RE) technique that increases the diversity of perturbations and reduces gradient fluctuations. Our method can be applied to any gradient-based attacks to make those attacks become more transferable. We evaluate our proposed method by attacking seven state-of-the-art (SOTA) deep learning models and comparing against five SOTA attacks; we also attack nine advanced defense mechanisms that are integrated into the above models. Our results demonstrate significant improvement on the attack success rate (ASR) and transferability when using our method alone, and that it can also be easily applied to other baseline methods (which are gradient-based) to substantially improve their performance. <\/jats:p>","DOI":"10.1142\/s2811032322500059","type":"journal-article","created":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T14:56:46Z","timestamp":1671202606000},"source":"Crossref","is-referenced-by-count":8,"title":["Black-Box Attack using Adversarial Examples: A New Method of Improving Transferability"],"prefix":"10.1142","volume":"01","author":[{"given":"Tao","family":"Wu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Missouri University of Science and Technology, Rolla, MO 65409, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2947-3111","authenticated-orcid":false,"given":"Tie","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Missouri University of Science and Technology, Rolla, MO 65409, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"suffix":"II","given":"Donald C.","family":"Wunsch","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO 65409, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"219","published-online":{"date-parts":[[2023,2,16]]},"reference":[{"key":"S2811032322500059BIB001","volume-title":"Proc Int Conf on Machine Learning","author":"Athalye A.","year":"2018"},{"key":"S2811032322500059BIB002","unstructured":"J. Byun,  S. Cho,  M.J. Kwon,  H.S. Kim and  C. Kim ,  Proc 2022 IEEE\/CVF Conf on Computer Vision and Pattern Recognition, 2022,  pp. 15244\u201315253."},{"key":"S2811032322500059BIB003","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"S2811032322500059BIB004","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"S2811032322500059BIB006","volume-title":"Proc Int Conf on Machine Learning","author":"Cohen J. M.","year":"2019"},{"key":"S2811032322500059BIB007","unstructured":"Y. Dong,  F. Liao,  T. Pang,  H. Su,  J. Zhu,  X. Hu and  J. Li ,  Proc 2018 IEEE Conf on Computer Vision and Pattern Recognition, 2018,  pp. 9185\u20139193."},{"key":"S2811032322500059BIB008","unstructured":"Y. Dong,  T. Pang,  H. Su and  J. Zhu ,  Proc 2019 IEEE\/CVF Conf on Computer Vision and Pattern Recognition, 2019,  pp. 4312\u20134321."},{"key":"S2811032322500059BIB010","volume-title":"Proc. Int. Conf. on Learning Representations","author":"Goodfellow I. J.","year":"2015"},{"key":"S2811032322500059BIB011","volume-title":"Proc. Int. Conf on Learning Representations","author":"Guo C.","year":"2018"},{"key":"S2811032322500059BIB012","volume-title":"Proc 34th Conf on Neural Information Processing Systems","author":"Guo Y.","year":"2020"},{"key":"S2811032322500059BIB013","unstructured":"K. He,  X. Zhang,  S. Ren and  J. Sun ,  Proc 2016 IEEE Conf on Computer Vision and Pattern Recognition, 2016,  pp. 770\u2013778."},{"key":"S2811032322500059BIB014","unstructured":"X. Jia,  X. Wei,  X. Cao and  H. Foroosh ,  Proc 2019 IEEE Conf on Computer Vision and Pattern Recognition, 2019,  pp. 6084\u20136092."},{"key":"S2811032322500059BIB016","volume-title":"Proc 5th Int Conf on Learning Representations","author":"Kurakin A.","year":"2017"},{"key":"S2811032322500059BIB017","volume-title":"Proc 5th Int Conf on Learning Representations","author":"Kurakin A.","year":"2017"},{"key":"S2811032322500059BIB018","doi-asserted-by":"crossref","unstructured":"Y. Li,  S. Bai,  Y. Zhou,  C. Xie,  Z. Zhang and  A. Yuille ,  Proc AAAI Conf on Artificial Intelligence, 2020, vol.  34,  pp. 11458\u201311465.","DOI":"10.1609\/aaai.v34i07.6810"},{"key":"S2811032322500059BIB019","unstructured":"F. Liao,  M. Liang,  Y. Dong,  T. Pang,  X. Hu and  J. Zhu ,  Proc 2018 IEEE Conf on Computer Vision and Pattern Recognition, 2018,  pp. 1778\u20131787."},{"key":"S2811032322500059BIB020","volume-title":"Proc 2020 Int Conf on Learning Representations","author":"Lin J.","year":"2020"},{"key":"S2811032322500059BIB021","unstructured":"X. Liu,  M. Cheng,  H. Zhang and  C.J. Hsieh ,  Proc European Conf on Computer Vision (ECCV), 2018,  pp. 369\u2013385."},{"key":"S2811032322500059BIB022","volume-title":"Proc Int Conf on Learning Representations","author":"Liu Y.","year":"2017"},{"key":"S2811032322500059BIB023","unstructured":"Z. Liu,  Q. Liu,  T. Liu,  N. Xu,  X. Lin,  Y. Wang and  W. Wen ,  Proc 2019 IEEE Conf on Computer Vision and Pattern Recognition, 2019,  pp. 860\u2013868."},{"key":"S2811032322500059BIB024","volume-title":"Proc Int Conf on Learning Representations","author":"Madry A.","year":"2018"},{"key":"S2811032322500059BIB025","unstructured":"M. Naseer,  S. Khan,  M. Hayat,  F. S. Khan and  F. Porikli ,  Proc 2020 IEEE\/CVF Conf on Computer Vision and Pattern Recognition, 2020,  pp. 262\u2013271."},{"key":"S2811032322500059BIB026","first-page":"543","volume":"269","author":"Nesterov Y.","year":"1983","journal-title":"Dokl. Akad. Nauk USSR"},{"key":"S2811032322500059BIB027","unstructured":"T. Pang,  K. Xu,  C. Du,  N. Chen and  J. Zhu ,  Proc Int Conf on Machine Learning, 2019,  pp. 4970\u20134979."},{"key":"S2811032322500059BIB028","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"S2811032322500059BIB029","volume-title":"Proc AAAI Conf on Artificial Intelligence","author":"Szegedy C.","year":"2017"},{"key":"S2811032322500059BIB030","unstructured":"C. Szegedy,  V. Vanhoucke,  S. Ioffe,  J. Shlens and  Z. Wojna ,  Proc 2016 IEEE Conf on Computer Vision and Pattern Recognition, 2016,  pp. 2818\u20132826."},{"key":"S2811032322500059BIB031","volume-title":"Proc Int Conf on Learning Representations","author":"Szegedy C.","year":"2014"},{"key":"S2811032322500059BIB033","volume-title":"Proc Int Conf on Learning Representations","author":"Tram\u00e8r F.","year":"2018"},{"key":"S2811032322500059BIB034","unstructured":"X. Wang,  A. Shrivastava and  A. Gupta ,  Proc 2017 IEEE Conf on Computer Vision and Pattern Recognition, 2017,  pp. 2606\u20132615."},{"key":"S2811032322500059BIB035","unstructured":"X. Wang and  K. He ,  Proc IEEE\/CVF Conf on Computer Vision and Pattern Recognition, 2021,  pp. 1924\u20131933."},{"key":"S2811032322500059BIB036","unstructured":"X. Wang,  X. He,  J. Wang and  K. He ,  Proc 2021 IEEE\/CVF Int Conf on Computer Vision (ICCV), 2021,  pp. 16158\u201316167."},{"key":"S2811032322500059BIB038","volume-title":"Proc Int Conf on Learning Representations","author":"Wu D.","year":"2019"},{"key":"S2811032322500059BIB039","volume-title":"Proc Int Conf on Learning Representations","author":"Xie C.","year":"2018"},{"key":"S2811032322500059BIB040","unstructured":"C. Xie,  Z. Zhang,  Y. Zhou,  S. Bai,  J. Wang,  Z. Ren and  A. L. Yuille ,  Proc 2019 IEEE\/CVF Conf on Computer Vision and Pattern Recognition, 2019,  pp. 2730\u20132739."},{"key":"S2811032322500059BIB041","volume-title":"Proc Network and Distributed System Security Symp","author":"Xu W.","year":"2018"},{"key":"S2811032322500059BIB042","unstructured":"Y. Zhang and  P. Liang ,  Proc 22nd Int Conf on Artificial Intelligence and Statistics, 2019,  pp. 684\u2013693."},{"key":"S2811032322500059BIB043","doi-asserted-by":"crossref","unstructured":"Z. Zhong,  L. Zheng,  G. Kang,  S. Li and  Y. Yang ,  Proc AAAI Conf on Artificial Intelligence, 2020, vol.  34,  pp. 13001\u201313008.","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"S2811032322500059BIB044","doi-asserted-by":"crossref","unstructured":"J. Zou,  Y. Duan,  B. Li,  W. Zhang,  Y. Pan and  Z. Pan ,  Proc AAAI Conf on Artificial Intelligence, 2022, vol.  36,  pp. 3662\u20133670.","DOI":"10.1609\/aaai.v36i3.20279"},{"key":"S2811032322500059BIB045","doi-asserted-by":"crossref","unstructured":"J. Zou,  Z. Pan,  J. Qiu,  X. Liu,  T. Rui and  W. Li ,  Proc European Conf on Computer Vision, 2020,  pp. 563\u2013579.","DOI":"10.1007\/978-3-030-58542-6_34"}],"container-title":["World Scientific Annual Review of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S2811032322500059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,28]],"date-time":"2024-03-28T03:20:26Z","timestamp":1711596026000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S2811032322500059"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":40,"alternative-id":["10.1142\/S2811032322500059"],"URL":"https:\/\/doi.org\/10.1142\/s2811032322500059","relation":{},"ISSN":["2811-0323","2811-0331"],"issn-type":[{"value":"2811-0323","type":"print"},{"value":"2811-0331","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]},"article-number":"2250005"}}