{"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/towards-large-yet-imperceptible-adversarial","title":"Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance","arxiv_id":"1911.02466","date":"2019-11-06","proceeding":"CVPR 2020 6","authors":["Zhengyu Zhao","Zhuoran Liu","Martha Larson"],"abstract":"The success of image perturbations that are designed to fool image classifier is assessed in terms of both adversarial effect and visual imperceptibility. The conventional assumption on imperceptibility is that perturbations should strive for tight $L_p$-norm bounds in RGB space. In this work, we drop this assumption by pursuing an approach that exploits human color perception, and more specifically, minimizing perturbation size with respect to perceptual color distance. Our first approach, Perceptual Color distance C&W (PerC-C&W), extends the widely-used C&W approach and produces larger RGB perturbations. PerC-C&W is able to maintain adversarial strength, while contributing to imperceptibility. Our second approach, Perceptual Color distance Alternating Loss (PerC-AL), achieves the same outcome, but does so more efficiently by alternating between the classification loss and perceptual color difference when updating perturbations. Experimental evaluation shows PerC approaches outperform conventional $L_p$ approaches in terms of robustness and transferability, and also demonstrates that the PerC distance can provide added value on top of existing structure-based methods to creating image perturbations.","url_abs":"https://arxiv.org/abs/1911.02466v2","url_pdf":"https://arxiv.org/pdf/1911.02466v2.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":"towards-large-yet-imperceptible-adversarial","repo_url":"https://github.com/ZhengyuZhao/PerC-Adversarial","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"towards-large-yet-imperceptible-adversarial","repo_url":"https://github.com/jeromerony/adversarial-library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1911.02466","atlas_url":"https://app.syntology.ai/?focus=1911.02466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.02466"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/ZhengyuZhao/PerC-Adversarial","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jeromerony/adversarial-library","reach":null}],"summary":{"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":0,"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":"404ede55dcc21fe2","entry":"quantization","repo":"ZhengyuZhao/PerC-Adversarial","repo_kind":"official","path":"perc_cw.py","file_url":"https://github.com/ZhengyuZhao/PerC-Adversarial/blob/HEAD/perc_cw.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"404ede55dcc21fe2"}},{"code_sha256_prefix":"c56c9f8b3a348e0a","entry":"perc_al","repo":"jeromerony/adversarial-library","repo_kind":"listed","path":"adv_lib/attacks/perceptual_color_attacks/perceptual_color_distance_al.py","file_url":"https://github.com/jeromerony/adversarial-library/blob/HEAD/adv_lib/attacks/perceptual_color_attacks/perceptual_color_distance_al.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c56c9f8b3a348e0a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}