{"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/sign-bits-are-all-you-need-for-black-box","title":"Sign Bits Are All You Need for Black-Box Attacks","arxiv_id":null,"date":"2020-05-01","proceeding":"ICLR 2020 1","authors":["Abdullah Al-Dujaili","Una-May O'Reilly"],"abstract":"We present a novel black-box adversarial attack algorithm with state-of-the-art model evasion rates for query efficiency under $\\ell_\\infty$ and $\\ell_2$ metrics. It exploits a \\textit{sign-based}, rather than magnitude-based, gradient estimation approach that shifts the gradient estimation from continuous to binary black-box optimization. It adaptively constructs queries to estimate the gradient, one query relying upon the previous, rather than re-estimating the gradient each step with random query construction. Its reliance on sign bits yields  a smaller memory footprint and it requires neither hyperparameter tuning or dimensionality reduction. Further, its theoretical performance is guaranteed and it can characterize  adversarial subspaces better than white-box gradient-aligned subspaces. On two public black-box attack challenges and a model robustly trained against transfer attacks, the algorithm's evasion rates surpass all submitted attacks. For a suite of published models,  the algorithm is $3.8\\times$ less failure-prone while spending $2.5\\times$  fewer queries versus the best combination of state of art algorithms. For example, it evades a standard MNIST model using just $12$ queries on average. Similar performance is observed on a standard IMAGENET model with an average of $579$ queries.","url_abs":"https://openreview.net/forum?id=SygW0TEFwH","url_pdf":"https://openreview.net/pdf?id=SygW0TEFwH","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":"sign-bits-are-all-you-need-for-black-box","repo_url":"https://github.com/ash-aldujaili/blackbox-adv-examples-signhunter","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"all","task_name":"All"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}