{"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/proper-network-interpretability-helps","title":"Proper Network Interpretability Helps Adversarial Robustness in Classification","arxiv_id":"2006.14748","date":"2020-06-26","proceeding":"ICML 2020 1","authors":["Akhilan Boopathy","Sijia Liu","Gaoyuan Zhang","Cynthia Liu","Pin-Yu Chen","Shiyu Chang","Luca Daniel"],"abstract":"Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to adversarial attacks. In this paper, we theoretically show that with a proper measurement of interpretation, it is actually difficult to prevent prediction-evasion adversarial attacks from causing interpretation discrepancy, as confirmed by experiments on MNIST, CIFAR-10 and Restricted ImageNet. Spurred by that, we develop an interpretability-aware defensive scheme built only on promoting robust interpretation (without the need for resorting to adversarial loss minimization). We show that our defense achieves both robust classification and robust interpretation, outperforming state-of-the-art adversarial training methods against attacks of large perturbation in particular.","url_abs":"https://arxiv.org/abs/2006.14748v2","url_pdf":"https://arxiv.org/pdf/2006.14748v2.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":"proper-network-interpretability-helps","repo_url":"https://github.com/AkhilanB/Proper-Interpretability","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"network-interpretation","task_name":"Network Interpretation"},{"task_slug":"robust-classification","task_name":"Robust classification"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.14748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.14748"}},"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/AkhilanB/Proper-Interpretability","reach":null}],"summary":{"ran":1,"ran_honours":2,"ran_draft_wrong":1,"ran_fixture":2,"unverified":11},"by_repo_kind":{"official":{"samples":16,"ran":6,"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":1,"samples":[{"code_sha256_prefix":"248795a472708ab1","entry":"Model","repo":"AkhilanB/Proper-Interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/AkhilanB/Proper-Interpretability/blob/HEAD/funcs.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":"248795a472708ab1"}},{"code_sha256_prefix":"86c9fa246614e9a9","entry":"extract_data","repo":"AkhilanB/Proper-Interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/AkhilanB/Proper-Interpretability/blob/HEAD/funcs.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"86c9fa246614e9a9"}},{"code_sha256_prefix":"a0cf6bb81ff7819e","entry":"extract_labels","repo":"AkhilanB/Proper-Interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/AkhilanB/Proper-Interpretability/blob/HEAD/funcs.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0cf6bb81ff7819e"}},{"code_sha256_prefix":"44b2739698e6b9ff","entry":"network_utils","repo":"akhilanb/proper-interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/akhilanb/proper-interpretability/blob/HEAD/funcs.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"44b2739698e6b9ff"}},{"code_sha256_prefix":"340b076210f6b91b","entry":"pearson_corr","repo":"akhilanb/proper-interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/akhilanb/proper-interpretability/blob/HEAD/funcs.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"340b076210f6b91b"}},{"code_sha256_prefix":"b0ac43c489760cb7","entry":"tau_corr","repo":"akhilanb/proper-interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/akhilanb/proper-interpretability/blob/HEAD/funcs.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0ac43c489760cb7"}},{"code_sha256_prefix":"274315bf19aca6bb","entry":"CIFAR","repo":"akhilanb/proper-interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/akhilanb/proper-interpretability/blob/HEAD/funcs.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":"274315bf19aca6bb"}},{"code_sha256_prefix":"055fc970fd1b2e16","entry":"CIFAR","repo":"AkhilanB/Proper-Interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/AkhilanB/Proper-Interpretability/blob/HEAD/funcs.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":"055fc970fd1b2e16"}},{"code_sha256_prefix":"ed99dc8820ef0915","entry":"MNIST","repo":"akhilanb/proper-interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/akhilanb/proper-interpretability/blob/HEAD/funcs.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":"ed99dc8820ef0915"}},{"code_sha256_prefix":"aeb5bbdc2435ad02","entry":"MNIST","repo":"AkhilanB/Proper-Interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/AkhilanB/Proper-Interpretability/blob/HEAD/funcs.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":"aeb5bbdc2435ad02"}},{"code_sha256_prefix":"d204828ab646c177","entry":"data_utils","repo":"akhilanb/proper-interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/akhilanb/proper-interpretability/blob/HEAD/funcs.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":"d204828ab646c177"}},{"code_sha256_prefix":"237912592df9d7cd","entry":"data_utils","repo":"AkhilanB/Proper-Interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/AkhilanB/Proper-Interpretability/blob/HEAD/funcs.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":"237912592df9d7cd"}},{"code_sha256_prefix":"4ee0a66577a407fe","entry":"isa_cam","repo":"akhilanb/proper-interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/akhilanb/proper-interpretability/blob/HEAD/funcs.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":"4ee0a66577a407fe"}},{"code_sha256_prefix":"30479e7f72f7afb2","entry":"isa_cam","repo":"AkhilanB/Proper-Interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/AkhilanB/Proper-Interpretability/blob/HEAD/funcs.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":"30479e7f72f7afb2"}},{"code_sha256_prefix":"3b4fb87c66244ebf","entry":"load_batch","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3b4fb87c66244ebf"}},{"code_sha256_prefix":"08cba5535c33775b","entry":"load_model","repo":"akhilanb/proper-interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/akhilanb/proper-interpretability/blob/HEAD/funcs.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":"08cba5535c33775b"}},{"code_sha256_prefix":"a6fba14f7d4610ed","entry":"load_model","repo":"AkhilanB/Proper-Interpretability","repo_kind":"official","path":"funcs.py","file_url":"https://github.com/AkhilanB/Proper-Interpretability/blob/HEAD/funcs.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":"a6fba14f7d4610ed"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}