{"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/shift-invariance-can-reduce-adversarial","title":"Shift Invariance Can Reduce Adversarial Robustness","arxiv_id":"2103.02695","date":"2021-03-03","proceeding":"NeurIPS 2021 12","authors":["Songwei Ge","Vasu Singla","Ronen Basri","David Jacobs"],"abstract":"Shift invariance is a critical property of CNNs that improves performance on classification. However, we show that invariance to circular shifts can also lead to greater sensitivity to adversarial attacks. We first characterize the margin between classes when a shift-invariant linear classifier is used. We show that the margin can only depend on the DC component of the signals. Then, using results about infinitely wide networks, we show that in some simple cases, fully connected and shift-invariant neural networks produce linear decision boundaries. Using this, we prove that shift invariance in neural networks produces adversarial examples for the simple case of two classes, each consisting of a single image with a black or white dot on a gray background. This is more than a curiosity; we show empirically that with real datasets and realistic architectures, shift invariance reduces adversarial robustness. Finally, we describe initial experiments using synthetic data to probe the source of this connection.","url_abs":"https://arxiv.org/abs/2103.02695v3","url_pdf":"https://arxiv.org/pdf/2103.02695v3.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":"shift-invariance-can-reduce-adversarial","repo_url":"https://github.com/SongweiGe/shift-invariance-adv-robustness","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.02695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.02695"}},"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":"deterministic:regex_extraction","url":"https://github.com/SongweiGe/shift-invariance-adv-robustness","reach":null}],"summary":{"ran_fixture":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"6295da24cd9b4a36","entry":"l2_norm","repo":"SongweiGe/shift-invariance-adv-robustness","repo_kind":"official","path":"5_1_5/test_cifar.py","file_url":"https://github.com/SongweiGe/shift-invariance-adv-robustness/blob/HEAD/5_1_5/test_cifar.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6295da24cd9b4a36"}},{"code_sha256_prefix":"d12867ab74a02a6c","entry":"squared_l2_norm","repo":"SongweiGe/shift-invariance-adv-robustness","repo_kind":"official","path":"5_1_5/test_cifar.py","file_url":"https://github.com/SongweiGe/shift-invariance-adv-robustness/blob/HEAD/5_1_5/test_cifar.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d12867ab74a02a6c"}},{"code_sha256_prefix":"9818a179216a2b9a","entry":"train","repo":"SongweiGe/shift-invariance-adv-robustness","repo_kind":"official","path":"5_1_1/train_mnist_full.py","file_url":"https://github.com/SongweiGe/shift-invariance-adv-robustness/blob/HEAD/5_1_1/train_mnist_full.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9818a179216a2b9a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}