{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SF5EPPS6KQGGLDU5ZUAGHWV75L","short_pith_number":"pith:SF5EPPS6","schema_version":"1.0","canonical_sha256":"917a47be5e540c658e9dcd0063dabfead7c7121053cc7a47f210cf4ddaa696bb","source":{"kind":"arxiv","id":"2011.10794","version":1},"attestation_state":"computed","paper":{"title":"Spatially Correlated Patterns in Adversarial Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anupam Chattopadhyay, Bryan Tan Bing Xing, Lionell Yip En Zhi, Nandish Chattopadhyay","submitted_at":"2020-11-21T14:06:59Z","abstract_excerpt":"Adversarial attacks have proved to be the major impediment in the progress on research towards reliable machine learning solutions. Carefully crafted perturbations, imperceptible to human vision, can be added to images to force misclassification by an otherwise high performing neural network. To have a better understanding of the key contributors of such structured attacks, we searched for and studied spatially co-located patterns in the distribution of pixels in the input space. In this paper, we propose a framework for segregating and isolating regions within an input image which are particu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2011.10794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-11-21T14:06:59Z","cross_cats_sorted":[],"title_canon_sha256":"b23a89bbd522503f5f9d4402ff8b308f5c4c0aa61b8517048017fbcbaca49e6d","abstract_canon_sha256":"7a0c011e60b0ecbfb37f53efbf2e1ff117cd95799380e6df4cdde3b7c539571c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:26.027778Z","signature_b64":"JJAdQkDVohPU1BVZZNinCklTAMDISHPae/NaXTJ65bGEyXJj9FcWBx6SCX9YyziQ4ekTs0Vc2wbthATCzt8dAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"917a47be5e540c658e9dcd0063dabfead7c7121053cc7a47f210cf4ddaa696bb","last_reissued_at":"2026-07-05T01:53:26.027402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:26.027402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatially Correlated Patterns in Adversarial Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anupam Chattopadhyay, Bryan Tan Bing Xing, Lionell Yip En Zhi, Nandish Chattopadhyay","submitted_at":"2020-11-21T14:06:59Z","abstract_excerpt":"Adversarial attacks have proved to be the major impediment in the progress on research towards reliable machine learning solutions. Carefully crafted perturbations, imperceptible to human vision, can be added to images to force misclassification by an otherwise high performing neural network. To have a better understanding of the key contributors of such structured attacks, we searched for and studied spatially co-located patterns in the distribution of pixels in the input space. In this paper, we propose a framework for segregating and isolating regions within an input image which are particu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.10794","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.10794/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2011.10794","created_at":"2026-07-05T01:53:26.027456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.10794v1","created_at":"2026-07-05T01:53:26.027456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.10794","created_at":"2026-07-05T01:53:26.027456+00:00"},{"alias_kind":"pith_short_12","alias_value":"SF5EPPS6KQGG","created_at":"2026-07-05T01:53:26.027456+00:00"},{"alias_kind":"pith_short_16","alias_value":"SF5EPPS6KQGGLDU5","created_at":"2026-07-05T01:53:26.027456+00:00"},{"alias_kind":"pith_short_8","alias_value":"SF5EPPS6","created_at":"2026-07-05T01:53:26.027456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SF5EPPS6KQGGLDU5ZUAGHWV75L","json":"https://pith.science/pith/SF5EPPS6KQGGLDU5ZUAGHWV75L.json","graph_json":"https://pith.science/api/pith-number/SF5EPPS6KQGGLDU5ZUAGHWV75L/graph.json","events_json":"https://pith.science/api/pith-number/SF5EPPS6KQGGLDU5ZUAGHWV75L/events.json","paper":"https://pith.science/paper/SF5EPPS6"},"agent_actions":{"view_html":"https://pith.science/pith/SF5EPPS6KQGGLDU5ZUAGHWV75L","download_json":"https://pith.science/pith/SF5EPPS6KQGGLDU5ZUAGHWV75L.json","view_paper":"https://pith.science/paper/SF5EPPS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.10794&json=true","fetch_graph":"https://pith.science/api/pith-number/SF5EPPS6KQGGLDU5ZUAGHWV75L/graph.json","fetch_events":"https://pith.science/api/pith-number/SF5EPPS6KQGGLDU5ZUAGHWV75L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SF5EPPS6KQGGLDU5ZUAGHWV75L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SF5EPPS6KQGGLDU5ZUAGHWV75L/action/storage_attestation","attest_author":"https://pith.science/pith/SF5EPPS6KQGGLDU5ZUAGHWV75L/action/author_attestation","sign_citation":"https://pith.science/pith/SF5EPPS6KQGGLDU5ZUAGHWV75L/action/citation_signature","submit_replication":"https://pith.science/pith/SF5EPPS6KQGGLDU5ZUAGHWV75L/action/replication_record"}},"created_at":"2026-07-05T01:53:26.027456+00:00","updated_at":"2026-07-05T01:53:26.027456+00:00"}