{"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/regional-image-perturbation-reduces-l-p-norms","title":"Regional Image Perturbation Reduces $L_p$ Norms of Adversarial Examples While Maintaining Model-to-model Transferability","arxiv_id":"2007.03198","date":"2020-07-07","proceeding":null,"authors":["Utku Ozbulak","Jonathan Peck","Wesley De Neve","Bart Goossens","Yvan Saeys","Arnout Van Messem"],"abstract":"Regional adversarial attacks often rely on complicated methods for generating adversarial perturbations, making it hard to compare their efficacy against well-known attacks. In this study, we show that effective regional perturbations can be generated without resorting to complex methods. We develop a very simple regional adversarial perturbation attack method using cross-entropy sign, one of the most commonly used losses in adversarial machine learning. Our experiments on ImageNet with multiple models reveal that, on average, $76\\%$ of the generated adversarial examples maintain model-to-model transferability when the perturbation is applied to local image regions. Depending on the selected region, these localized adversarial examples require significantly less $L_p$ norm distortion (for $p \\in \\{0, 2, \\infty\\}$) compared to their non-local counterparts. These localized attacks therefore have the potential to undermine defenses that claim robustness under the aforementioned norms.","url_abs":"https://arxiv.org/abs/2007.03198v2","url_pdf":"https://arxiv.org/pdf/2007.03198v2.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":"regional-image-perturbation-reduces-l-p-norms","repo_url":"https://github.com/utkuozbulak/regional-adversarial-perturbation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.03198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.03198"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/utkuozbulak/regional-adversarial-perturbation","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"128bc52292e13b2c","entry":"RegionalAdversarialAttack","repo":"utkuozbulak/regional-adversarial-perturbation","repo_kind":"official","path":"src/regional_attack.py","file_url":"https://github.com/utkuozbulak/regional-adversarial-perturbation/blob/HEAD/src/regional_attack.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"128bc52292e13b2c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}