{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SFPVLD4GXK7WEG4VTO4BIWZL2H","short_pith_number":"pith:SFPVLD4G","schema_version":"1.0","canonical_sha256":"915f558f86babf621b959bb8145b2bd1ce20760b8966ea4965d78d25e202e650","source":{"kind":"arxiv","id":"1707.03501","version":1},"attestation_state":"computed","paper":{"title":"NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CV","authors_text":"David Forsyth, Evan Fabry, Hussein Sibai, Jiajun Lu","submitted_at":"2017-07-12T00:09:50Z","abstract_excerpt":"It has been shown that most machine learning algorithms are susceptible to adversarial perturbations. Slightly perturbing an image in a carefully chosen direction in the image space may cause a trained neural network model to misclassify it. Recently, it was shown that physical adversarial examples exist: printing perturbed images then taking pictures of them would still result in misclassification. This raises security and safety concerns.\n  However, these experiments ignore a crucial property of physical objects: the camera can view objects from different distances and at different angles. I"},"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":"1707.03501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-12T00:09:50Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"c0734f1677adc97109d729b777ef9cd18f4d3e9335081736149490bc84d810ca","abstract_canon_sha256":"e562f47af28390e582cfc13abd6045d7c347084d3d563ee5a9827f2f5947406b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:25.813689Z","signature_b64":"m269u/x0kNTjttvMWs8RmoY1gYteF1fwtLlGHSq3lL5x2sJe6G5KVbLPzPK3/xNJliGRRHaLf0V7VE/xNImgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"915f558f86babf621b959bb8145b2bd1ce20760b8966ea4965d78d25e202e650","last_reissued_at":"2026-05-18T00:40:25.813160Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:25.813160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CV","authors_text":"David Forsyth, Evan Fabry, Hussein Sibai, Jiajun Lu","submitted_at":"2017-07-12T00:09:50Z","abstract_excerpt":"It has been shown that most machine learning algorithms are susceptible to adversarial perturbations. Slightly perturbing an image in a carefully chosen direction in the image space may cause a trained neural network model to misclassify it. Recently, it was shown that physical adversarial examples exist: printing perturbed images then taking pictures of them would still result in misclassification. This raises security and safety concerns.\n  However, these experiments ignore a crucial property of physical objects: the camera can view objects from different distances and at different angles. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03501","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":""},"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":"1707.03501","created_at":"2026-05-18T00:40:25.813249+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.03501v1","created_at":"2026-05-18T00:40:25.813249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03501","created_at":"2026-05-18T00:40:25.813249+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFPVLD4GXK7W","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFPVLD4GXK7WEG4V","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFPVLD4G","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1907.00374","citing_title":"Fooling a Real Car with Adversarial Traffic Signs","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01051","citing_title":"ML-based Fault Injection for Autonomous Vehicles: A Case for Bayesian Fault Injection","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"1907.01996","citing_title":"Robust Synthesis of Adversarial Visual Examples Using a Deep Image Prior","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07379","citing_title":"RELO: Reinforcement Learning to Localize for Visual Object Tracking","ref_index":201,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07379","citing_title":"RELO: Reinforcement Learning to Localize for Visual Object Tracking","ref_index":200,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SFPVLD4GXK7WEG4VTO4BIWZL2H","json":"https://pith.science/pith/SFPVLD4GXK7WEG4VTO4BIWZL2H.json","graph_json":"https://pith.science/api/pith-number/SFPVLD4GXK7WEG4VTO4BIWZL2H/graph.json","events_json":"https://pith.science/api/pith-number/SFPVLD4GXK7WEG4VTO4BIWZL2H/events.json","paper":"https://pith.science/paper/SFPVLD4G"},"agent_actions":{"view_html":"https://pith.science/pith/SFPVLD4GXK7WEG4VTO4BIWZL2H","download_json":"https://pith.science/pith/SFPVLD4GXK7WEG4VTO4BIWZL2H.json","view_paper":"https://pith.science/paper/SFPVLD4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.03501&json=true","fetch_graph":"https://pith.science/api/pith-number/SFPVLD4GXK7WEG4VTO4BIWZL2H/graph.json","fetch_events":"https://pith.science/api/pith-number/SFPVLD4GXK7WEG4VTO4BIWZL2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFPVLD4GXK7WEG4VTO4BIWZL2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFPVLD4GXK7WEG4VTO4BIWZL2H/action/storage_attestation","attest_author":"https://pith.science/pith/SFPVLD4GXK7WEG4VTO4BIWZL2H/action/author_attestation","sign_citation":"https://pith.science/pith/SFPVLD4GXK7WEG4VTO4BIWZL2H/action/citation_signature","submit_replication":"https://pith.science/pith/SFPVLD4GXK7WEG4VTO4BIWZL2H/action/replication_record"}},"created_at":"2026-05-18T00:40:25.813249+00:00","updated_at":"2026-05-18T00:40:25.813249+00:00"}