{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:B4MTMC3USOF232KV7C3Z2MP34Z","short_pith_number":"pith:B4MTMC3U","schema_version":"1.0","canonical_sha256":"0f19360b74938bade955f8b79d31fbe65d8b12d9da1e791d0ca1dececbaaaba1","source":{"kind":"arxiv","id":"2012.11442","version":1},"attestation_state":"computed","paper":{"title":"Blurring Fools the Network -- Adversarial Attacks by Feature Peak Suppression and Gaussian Blurring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chenchen Zhao, Hao Li","submitted_at":"2020-12-21T15:47:14Z","abstract_excerpt":"Existing pixel-level adversarial attacks on neural networks may be deficient in real scenarios, since pixel-level changes on the data cannot be fully delivered to the neural network after camera capture and multiple image preprocessing steps. In contrast, in this paper, we argue from another perspective that gaussian blurring, a common technique of image preprocessing, can be aggressive itself in specific occasions, thus exposing the network to real-world adversarial attacks. We first propose an adversarial attack demo named peak suppression (PS) by suppressing the values of peak elements in t"},"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":"2012.11442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-21T15:47:14Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"1adb1e0c68bec3fd65a1f9cb19fe01031b01fb9f3184193cbec113514961fd97","abstract_canon_sha256":"de086b494e80ceb6ae0eb1f1f88c665325cf5b46ac636b76741cb6f79c061819"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:01:01.866563Z","signature_b64":"CH3y2W8AMXwXhnCkJ1x8zUxGk1P/eRnb/XfFp0Cuo1BxNGSwlYdxWP58ngM36FU2Bc/53jRd1bOfgX3iEq4iCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f19360b74938bade955f8b79d31fbe65d8b12d9da1e791d0ca1dececbaaaba1","last_reissued_at":"2026-07-05T02:01:01.866049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:01:01.866049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blurring Fools the Network -- Adversarial Attacks by Feature Peak Suppression and Gaussian Blurring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chenchen Zhao, Hao Li","submitted_at":"2020-12-21T15:47:14Z","abstract_excerpt":"Existing pixel-level adversarial attacks on neural networks may be deficient in real scenarios, since pixel-level changes on the data cannot be fully delivered to the neural network after camera capture and multiple image preprocessing steps. In contrast, in this paper, we argue from another perspective that gaussian blurring, a common technique of image preprocessing, can be aggressive itself in specific occasions, thus exposing the network to real-world adversarial attacks. We first propose an adversarial attack demo named peak suppression (PS) by suppressing the values of peak elements in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.11442","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/2012.11442/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":"2012.11442","created_at":"2026-07-05T02:01:01.866102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.11442v1","created_at":"2026-07-05T02:01:01.866102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.11442","created_at":"2026-07-05T02:01:01.866102+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4MTMC3USOF2","created_at":"2026-07-05T02:01:01.866102+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4MTMC3USOF232KV","created_at":"2026-07-05T02:01:01.866102+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4MTMC3U","created_at":"2026-07-05T02:01:01.866102+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02665","citing_title":"Beyond Invisibility: Learning Robust Visible Watermarks for Stronger Copyright Protection","ref_index":84,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4MTMC3USOF232KV7C3Z2MP34Z","json":"https://pith.science/pith/B4MTMC3USOF232KV7C3Z2MP34Z.json","graph_json":"https://pith.science/api/pith-number/B4MTMC3USOF232KV7C3Z2MP34Z/graph.json","events_json":"https://pith.science/api/pith-number/B4MTMC3USOF232KV7C3Z2MP34Z/events.json","paper":"https://pith.science/paper/B4MTMC3U"},"agent_actions":{"view_html":"https://pith.science/pith/B4MTMC3USOF232KV7C3Z2MP34Z","download_json":"https://pith.science/pith/B4MTMC3USOF232KV7C3Z2MP34Z.json","view_paper":"https://pith.science/paper/B4MTMC3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.11442&json=true","fetch_graph":"https://pith.science/api/pith-number/B4MTMC3USOF232KV7C3Z2MP34Z/graph.json","fetch_events":"https://pith.science/api/pith-number/B4MTMC3USOF232KV7C3Z2MP34Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4MTMC3USOF232KV7C3Z2MP34Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4MTMC3USOF232KV7C3Z2MP34Z/action/storage_attestation","attest_author":"https://pith.science/pith/B4MTMC3USOF232KV7C3Z2MP34Z/action/author_attestation","sign_citation":"https://pith.science/pith/B4MTMC3USOF232KV7C3Z2MP34Z/action/citation_signature","submit_replication":"https://pith.science/pith/B4MTMC3USOF232KV7C3Z2MP34Z/action/replication_record"}},"created_at":"2026-07-05T02:01:01.866102+00:00","updated_at":"2026-07-05T02:01:01.866102+00:00"}