{"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/multi-attacks-many-images-the-same","title":"Multi-attacks: Many images $+$ the same adversarial attack $\\to$ many target labels","arxiv_id":"2308.03792","date":"2023-08-04","proceeding":null,"authors":["Stanislav Fort"],"abstract":"We show that we can easily design a single adversarial perturbation $P$ that changes the class of $n$ images $X_1,X_2,\\dots,X_n$ from their original, unperturbed classes $c_1, c_2,\\dots,c_n$ to desired (not necessarily all the same) classes $c^*_1,c^*_2,\\dots,c^*_n$ for up to hundreds of images and target classes at once. We call these \\textit{multi-attacks}. Characterizing the maximum $n$ we can achieve under different conditions such as image resolution, we estimate the number of regions of high class confidence around a particular image in the space of pixels to be around $10^{\\mathcal{O}(100)}$, posing a significant problem for exhaustive defense strategies. We show several immediate consequences of this: adversarial attacks that change the resulting class based on their intensity, and scale-independent adversarial examples. To demonstrate the redundancy and richness of class decision boundaries in the pixel space, we look for its two-dimensional sections that trace images and spell words using particular classes. We also show that ensembling reduces susceptibility to multi-attacks, and that classifiers trained on random labels are more susceptible. Our code is available on GitHub.","url_abs":"https://arxiv.org/abs/2308.03792v1","url_pdf":"https://arxiv.org/pdf/2308.03792v1.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":"multi-attacks-many-images-the-same","repo_url":"https://github.com/stanislavfort/multi-attacks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.03792","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}