{"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/masking-adversarial-damage-finding","title":"Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network","arxiv_id":"2204.02738","date":"2022-04-06","proceeding":"CVPR 2022 1","authors":["Byung-Kwan Lee","Junho Kim","Yong Man Ro"],"abstract":"Adversarial examples provoke weak reliability and potential security issues in deep neural networks. Although adversarial training has been widely studied to improve adversarial robustness, it works in an over-parameterized regime and requires high computations and large memory budgets. To bridge adversarial robustness and model compression, we propose a novel adversarial pruning method, Masking Adversarial Damage (MAD) that employs second-order information of adversarial loss. By using it, we can accurately estimate adversarial saliency for model parameters and determine which parameters can be pruned without weakening adversarial robustness. Furthermore, we reveal that model parameters of initial layer are highly sensitive to the adversarial examples and show that compressed feature representation retains semantic information for the target objects. Through extensive experiments on three public datasets, we demonstrate that MAD effectively prunes adversarially trained networks without loosing adversarial robustness and shows better performance than previous adversarial pruning methods.","url_abs":"https://arxiv.org/abs/2204.02738v1","url_pdf":"https://arxiv.org/pdf/2204.02738v1.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":"masking-adversarial-damage-finding","repo_url":"https://github.com/ByungKwanLee/Masking-Adversarial-Damage","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"model-compression","task_name":"Model Compression"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.02738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02738"}},"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/ByungKwanLee/Masking-Adversarial-Damage","reach":null}],"summary":{"ran":1,"ran_fixture":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"543c33b7a3df7413","entry":"Conv2d_mask","repo":"ByungKwanLee/Masking-Adversarial-Damage","repo_kind":"official","path":"models/operator/mask.py","file_url":"https://github.com/ByungKwanLee/Masking-Adversarial-Damage/blob/HEAD/models/operator/mask.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":"543c33b7a3df7413"}},{"code_sha256_prefix":"c69509c702f9ebb9","entry":"f","repo":"ByungKwanLee/Masking-Adversarial-Damage","repo_kind":"official","path":"models/operator/mask.py","file_url":"https://github.com/ByungKwanLee/Masking-Adversarial-Damage/blob/HEAD/models/operator/mask.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c69509c702f9ebb9"}},{"code_sha256_prefix":"80f3a3eaa7200f70","entry":"f_inv","repo":"ByungKwanLee/Masking-Adversarial-Damage","repo_kind":"official","path":"models/operator/mask.py","file_url":"https://github.com/ByungKwanLee/Masking-Adversarial-Damage/blob/HEAD/models/operator/mask.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"80f3a3eaa7200f70"}},{"code_sha256_prefix":"10502db23508f715","entry":"operator","repo":"ByungKwanLee/Masking-Adversarial-Damage","repo_kind":"official","path":"models/operator/mask.py","file_url":"https://github.com/ByungKwanLee/Masking-Adversarial-Damage/blob/HEAD/models/operator/mask.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10502db23508f715"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}