{"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/advdrop-adversarial-attack-to-dnns-by","title":"AdvDrop: Adversarial Attack to DNNs by Dropping Information","arxiv_id":"2108.09034","date":"2021-08-20","proceeding":"ICCV 2021 10","authors":["Ranjie Duan","Yuefeng Chen","Dantong Niu","Yun Yang","A. K. Qin","Yuan He"],"abstract":"Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e.g. cartoon. However, in terms of visual perception of Deep Neural Networks (DNNs), the ability for recognizing abstract objects (visual objects with lost information) is still a challenge. In this work, we investigate this issue from an adversarial viewpoint: will the performance of DNNs decrease even for the images only losing a little information? Towards this end, we propose a novel adversarial attack, named \\textit{AdvDrop}, which crafts adversarial examples by dropping existing information of images. Previously, most adversarial attacks add extra disturbing information on clean images explicitly. Opposite to previous works, our proposed work explores the adversarial robustness of DNN models in a novel perspective by dropping imperceptible details to craft adversarial examples. We demonstrate the effectiveness of \\textit{AdvDrop} by extensive experiments, and show that this new type of adversarial examples is more difficult to be defended by current defense systems.","url_abs":"https://arxiv.org/abs/2108.09034v1","url_pdf":"https://arxiv.org/pdf/2108.09034v1.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":"advdrop-adversarial-attack-to-dnns-by","repo_url":"https://github.com/rjduan/advdrop","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2108.09034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.09034"}},"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/rjduan/advdrop","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":8},"by_repo_kind":{"official":{"samples":10,"ran":2,"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":"37251df462837488","entry":"diff_round","repo":"rjduan/advdrop","repo_kind":"official","path":"utils.py","file_url":"https://github.com/rjduan/advdrop/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"37251df462837488"}},{"code_sha256_prefix":"8ae1de364298b758","entry":"quality_to_factor","repo":"rjduan/advdrop","repo_kind":"official","path":"utils.py","file_url":"https://github.com/rjduan/advdrop/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ae1de364298b758"}},{"code_sha256_prefix":"596cb14b592e24f4","entry":"c_dequantize","repo":"rjduan/advdrop","repo_kind":"official","path":"decompression.py","file_url":"https://github.com/rjduan/advdrop/blob/HEAD/decompression.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"596cb14b592e24f4"}},{"code_sha256_prefix":"a9d0f5460a619666","entry":"dequantize","repo":"rjduan/advdrop","repo_kind":"official","path":"decompression.py","file_url":"https://github.com/rjduan/advdrop/blob/HEAD/decompression.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9d0f5460a619666"}},{"code_sha256_prefix":"c8febed4b57496fc","entry":"phi_diff","repo":"rjduan/advdrop","repo_kind":"official","path":"utils.py","file_url":"https://github.com/rjduan/advdrop/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c8febed4b57496fc"}},{"code_sha256_prefix":"b913e382e34034a5","entry":"pred_label_and_confidence","repo":"rjduan/advdrop","repo_kind":"official","path":"infod_sample.py","file_url":"https://github.com/rjduan/advdrop/blob/HEAD/infod_sample.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b913e382e34034a5"}},{"code_sha256_prefix":"9f06caf2e03e050d","entry":"rgb_to_ycbcr","repo":"rjduan/advdrop","repo_kind":"official","path":"compression.py","file_url":"https://github.com/rjduan/advdrop/blob/HEAD/compression.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f06caf2e03e050d"}},{"code_sha256_prefix":"c93c595b23ffc2cd","entry":"rgb_to_ycbcr_jpeg","repo":"rjduan/advdrop","repo_kind":"official","path":"compression.py","file_url":"https://github.com/rjduan/advdrop/blob/HEAD/compression.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c93c595b23ffc2cd"}},{"code_sha256_prefix":"ad42dc86b651cdba","entry":"sgn","repo":"rjduan/advdrop","repo_kind":"official","path":"compression.py","file_url":"https://github.com/rjduan/advdrop/blob/HEAD/compression.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ad42dc86b651cdba"}},{"code_sha256_prefix":"d86df89e5f91da6a","entry":"y_dequantize","repo":"rjduan/advdrop","repo_kind":"official","path":"decompression.py","file_url":"https://github.com/rjduan/advdrop/blob/HEAD/decompression.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d86df89e5f91da6a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}