{"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/interpreting-adversarially-trained","title":"Interpreting Adversarially Trained Convolutional Neural Networks","arxiv_id":"1905.09797","date":"2019-05-23","proceeding":null,"authors":["Tianyuan Zhang","Zhanxing Zhu"],"abstract":"We attempt to interpret how adversarially trained convolutional neural networks (AT-CNNs) recognize objects. We design systematic approaches to interpret AT-CNNs in both qualitative and quantitative ways and compare them with normally trained models. Surprisingly, we find that adversarial training alleviates the texture bias of standard CNNs when trained on object recognition tasks, and helps CNNs learn a more shape-biased representation. We validate our hypothesis from two aspects. First, we compare the salience maps of AT-CNNs and standard CNNs on clean images and images under different transformations. The comparison could visually show that the prediction of the two types of CNNs is sensitive to dramatically different types of features. Second, to achieve quantitative verification, we construct additional test datasets that destroy either textures or shapes, such as style-transferred version of clean data, saturated images and patch-shuffled ones, and then evaluate the classification accuracy of AT-CNNs and normal CNNs on these datasets. Our findings shed some light on why AT-CNNs are more robust than those normally trained ones and contribute to a better understanding of adversarial training over CNNs from an interpretation perspective.","url_abs":"https://arxiv.org/abs/1905.09797v1","url_pdf":"https://arxiv.org/pdf/1905.09797v1.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":"interpreting-adversarially-trained","repo_url":"https://github.com/PKUAI26/AT-CNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1905.09797","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.09797"}},"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/PKUAI26/AT-CNN","reach":null}],"summary":{"ran_draft_wrong":2,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"961f4afe1fc01e6c","entry":"GetSmoothGrad","repo":"PKUAI26/AT-CNN","repo_kind":"official","path":"code/baseline/utils.py","file_url":"https://github.com/PKUAI26/AT-CNN/blob/HEAD/code/baseline/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"961f4afe1fc01e6c"}},{"code_sha256_prefix":"6326abcd2dd15332","entry":"clip_eta","repo":"PKUAI26/AT-CNN","repo_kind":"official","path":"code/baseline/attack.py","file_url":"https://github.com/PKUAI26/AT-CNN/blob/HEAD/code/baseline/attack.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6326abcd2dd15332"}},{"code_sha256_prefix":"39a75e1aa853a0ae","entry":"fsgm","repo":"PKUAI26/AT-CNN","repo_kind":"official","path":"code/baseline/attack.py","file_url":"https://github.com/PKUAI26/AT-CNN/blob/HEAD/code/baseline/attack.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"39a75e1aa853a0ae"}},{"code_sha256_prefix":"26a741bdccd7cefe","entry":"clip_gradmap","repo":"PKUAI26/AT-CNN","repo_kind":"official","path":"code/baseline/utils.py","file_url":"https://github.com/PKUAI26/AT-CNN/blob/HEAD/code/baseline/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"26a741bdccd7cefe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}