{"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/smoothed-geometry-for-robust-attribution","title":"Smoothed Geometry for Robust Attribution","arxiv_id":"2006.06643","date":"2020-06-11","proceeding":"NeurIPS 2020 12","authors":["Zifan Wang","Haofan Wang","Shakul Ramkumar","Matt Fredrikson","Piotr Mardziel","Anupam Datta"],"abstract":"Feature attributions are a popular tool for explaining the behavior of Deep Neural Networks (DNNs), but have recently been shown to be vulnerable to attacks that produce divergent explanations for nearby inputs. This lack of robustness is especially problematic in high-stakes applications where adversarially-manipulated explanations could impair safety and trustworthiness. Building on a geometric understanding of these attacks presented in recent work, we identify Lipschitz continuity conditions on models' gradient that lead to robust gradient-based attributions, and observe that smoothness may also be related to the ability of an attack to transfer across multiple attribution methods. To mitigate these attacks in practice, we propose an inexpensive regularization method that promotes these conditions in DNNs, as well as a stochastic smoothing technique that does not require re-training. Our experiments on a range of image models demonstrate that both of these mitigations consistently improve attribution robustness, and confirm the role that smooth geometry plays in these attacks on real, large-scale models.","url_abs":"https://arxiv.org/abs/2006.06643v2","url_pdf":"https://arxiv.org/pdf/2006.06643v2.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":"smoothed-geometry-for-robust-attribution","repo_url":"https://github.com/zifanw/smoothed_geometry","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.06643","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06643"}},"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/zifanw/smoothed_geometry","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"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":"67e18e3fdd805d03","entry":"lr_schedule","repo":"zifanw/smoothed_geometry","repo_kind":"official","path":"models/keras_model.py","file_url":"https://github.com/zifanw/smoothed_geometry/blob/HEAD/models/keras_model.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"67e18e3fdd805d03"}},{"code_sha256_prefix":"e8cce4587fde5f47","entry":"BetaLoss","repo":"zifanw/smoothed_geometry","repo_kind":"official","path":"robust/smooth_space.py","file_url":"https://github.com/zifanw/smoothed_geometry/blob/HEAD/robust/smooth_space.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":"e8cce4587fde5f47"}},{"code_sha256_prefix":"f9c81687f57290ac","entry":"compute_W","repo":"zifanw/smoothed_geometry","repo_kind":"official","path":"robust/smooth_space.py","file_url":"https://github.com/zifanw/smoothed_geometry/blob/HEAD/robust/smooth_space.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":"f9c81687f57290ac"}},{"code_sha256_prefix":"7c10248ed4cd4926","entry":"resnet_layer","repo":"zifanw/smoothed_geometry","repo_kind":"official","path":"models/keras_model.py","file_url":"https://github.com/zifanw/smoothed_geometry/blob/HEAD/models/keras_model.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":"7c10248ed4cd4926"}},{"code_sha256_prefix":"9f3315577c74cf33","entry":"resnet_v1","repo":"zifanw/smoothed_geometry","repo_kind":"official","path":"models/keras_model.py","file_url":"https://github.com/zifanw/smoothed_geometry/blob/HEAD/models/keras_model.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":"9f3315577c74cf33"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}