{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YVSNA7NUM7JU3O5KPJ36VRI75A","short_pith_number":"pith:YVSNA7NU","schema_version":"1.0","canonical_sha256":"c564d07db467d34dbbaa7a77eac51fe81918b88519896d01d2e3378445719d32","source":{"kind":"arxiv","id":"2002.07088","version":6},"attestation_state":"computed","paper":{"title":"GRAPHITE: Generating Automatic Physical Examples for Machine-Learning Attacks on Computer Vision Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Atul Prakash, Earlence Fernandes, Jiefeng Chen, Neal Mangaokar, Ryan Feng, Somesh Jha","submitted_at":"2020-02-17T17:24:14Z","abstract_excerpt":"This paper investigates an adversary's ease of attack in generating adversarial examples for real-world scenarios. We address three key requirements for practical attacks for the real-world: 1) automatically constraining the size and shape of the attack so it can be applied with stickers, 2) transform-robustness, i.e., robustness of a attack to environmental physical variations such as viewpoint and lighting changes, and 3) supporting attacks in not only white-box, but also black-box hard-label scenarios, so that the adversary can attack proprietary models. In this work, we propose GRAPHITE, a"},"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":"2002.07088","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-02-17T17:24:14Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"9e2acb7ea6623b1d22e91de84f815afc59e7552666c83001bb371da81355cd9f","abstract_canon_sha256":"ff32f3814a03f04f3ca9bbadfebe5d9e2f55f02bbfaabb299f3b4b64c3f5cc0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:11.184833Z","signature_b64":"Mglc9zGV466Vz/xZItcIFDlevHsOz0lV1llcJZBFqL+BjI+miu4XmE6Zi3jxvStu9EvbgjI0m3UNdv3OlNMgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c564d07db467d34dbbaa7a77eac51fe81918b88519896d01d2e3378445719d32","last_reissued_at":"2026-07-05T04:00:11.184410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:11.184410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRAPHITE: Generating Automatic Physical Examples for Machine-Learning Attacks on Computer Vision Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Atul Prakash, Earlence Fernandes, Jiefeng Chen, Neal Mangaokar, Ryan Feng, Somesh Jha","submitted_at":"2020-02-17T17:24:14Z","abstract_excerpt":"This paper investigates an adversary's ease of attack in generating adversarial examples for real-world scenarios. We address three key requirements for practical attacks for the real-world: 1) automatically constraining the size and shape of the attack so it can be applied with stickers, 2) transform-robustness, i.e., robustness of a attack to environmental physical variations such as viewpoint and lighting changes, and 3) supporting attacks in not only white-box, but also black-box hard-label scenarios, so that the adversary can attack proprietary models. In this work, we propose GRAPHITE, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07088","kind":"arxiv","version":6},"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/2002.07088/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":"2002.07088","created_at":"2026-07-05T04:00:11.184467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.07088v6","created_at":"2026-07-05T04:00:11.184467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07088","created_at":"2026-07-05T04:00:11.184467+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVSNA7NUM7JU","created_at":"2026-07-05T04:00:11.184467+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVSNA7NUM7JU3O5K","created_at":"2026-07-05T04:00:11.184467+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVSNA7NU","created_at":"2026-07-05T04:00:11.184467+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/YVSNA7NUM7JU3O5KPJ36VRI75A","json":"https://pith.science/pith/YVSNA7NUM7JU3O5KPJ36VRI75A.json","graph_json":"https://pith.science/api/pith-number/YVSNA7NUM7JU3O5KPJ36VRI75A/graph.json","events_json":"https://pith.science/api/pith-number/YVSNA7NUM7JU3O5KPJ36VRI75A/events.json","paper":"https://pith.science/paper/YVSNA7NU"},"agent_actions":{"view_html":"https://pith.science/pith/YVSNA7NUM7JU3O5KPJ36VRI75A","download_json":"https://pith.science/pith/YVSNA7NUM7JU3O5KPJ36VRI75A.json","view_paper":"https://pith.science/paper/YVSNA7NU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.07088&json=true","fetch_graph":"https://pith.science/api/pith-number/YVSNA7NUM7JU3O5KPJ36VRI75A/graph.json","fetch_events":"https://pith.science/api/pith-number/YVSNA7NUM7JU3O5KPJ36VRI75A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVSNA7NUM7JU3O5KPJ36VRI75A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVSNA7NUM7JU3O5KPJ36VRI75A/action/storage_attestation","attest_author":"https://pith.science/pith/YVSNA7NUM7JU3O5KPJ36VRI75A/action/author_attestation","sign_citation":"https://pith.science/pith/YVSNA7NUM7JU3O5KPJ36VRI75A/action/citation_signature","submit_replication":"https://pith.science/pith/YVSNA7NUM7JU3O5KPJ36VRI75A/action/replication_record"}},"created_at":"2026-07-05T04:00:11.184467+00:00","updated_at":"2026-07-05T04:00:11.184467+00:00"}