{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/direction-aggregated-attack-for-transferable","title":"Direction-Aggregated Attack for Transferable Adversarial Examples","arxiv_id":"2104.09172","date":"2021-04-19","proceeding":null,"authors":["Tianjin Huang","Vlado Menkovski","Yulong Pei","Yuhao Wang","Mykola Pechenizkiy"],"abstract":"Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters are available. Finding adversarial examples that are transferable to other models or developed in a black-box setting is significantly more difficult. In this paper, we propose the Direction-Aggregated adversarial attacks that deliver transferable adversarial examples. Our method utilizes aggregated direction during the attack process for avoiding the generated adversarial examples overfitting to the white-box model. Extensive experiments on ImageNet show that our proposed method improves the transferability of adversarial examples significantly and outperforms state-of-the-art attacks, especially against adversarial robust models. The best averaged attack success rates of our proposed method reaches 94.6\\% against three adversarial trained models and 94.8\\% against five defense methods. It also reveals that current defense approaches do not prevent transferable adversarial attacks.","url_abs":"https://arxiv.org/abs/2104.09172v2","url_pdf":"https://arxiv.org/pdf/2104.09172v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"direction-aggregated-attack-for-transferable","repo_url":"https://github.com/Juintin/DA-Attack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.09172","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}