{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:J6OSRKNM4EOVTMHFVUEXNX5Q6N","short_pith_number":"pith:J6OSRKNM","schema_version":"1.0","canonical_sha256":"4f9d28a9ace11d59b0e5ad0976dfb0f3552bed2c8d2bc1111670fa69eec03b72","source":{"kind":"arxiv","id":"1808.02651","version":2},"attestation_state":"computed","paper":{"title":"Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.GR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alec Jacobson, Chun-Liang Li, Derek Nowrouzezahrai, Hsueh-Ti Derek Liu, Michael Tao","submitted_at":"2018-08-08T08:01:18Z","abstract_excerpt":"Many machine learning image classifiers are vulnerable to adversarial attacks, inputs with perturbations designed to intentionally trigger misclassification. Current adversarial methods directly alter pixel colors and evaluate against pixel norm-balls: pixel perturbations smaller than a specified magnitude, according to a measurement norm. This evaluation, however, has limited practical utility since perturbations in the pixel space do not correspond to underlying real-world phenomena of image formation that lead to them and has no security motivation attached. Pixels in natural images are mea"},"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":"1808.02651","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-08T08:01:18Z","cross_cats_sorted":["cs.CV","cs.GR","stat.ML"],"title_canon_sha256":"5fab761c1d0fe7d29d836ef5940d8a9c00c7f6afe6dcfba3bece449b34213d19","abstract_canon_sha256":"755938171a7ec6994c05f4a345e001289b42e90f89ab5c274ddd41f41e924c19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:51.062421Z","signature_b64":"nUoGA1LovbABnbndviwOyjnvHGwU69/l+JQk6/a9f6MuO4QFqW5dBTv5bUrh103PML0JjA6Dmx1r9/Kk4hq/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f9d28a9ace11d59b0e5ad0976dfb0f3552bed2c8d2bc1111670fa69eec03b72","last_reissued_at":"2026-05-17T23:53:51.061731Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:51.061731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.GR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alec Jacobson, Chun-Liang Li, Derek Nowrouzezahrai, Hsueh-Ti Derek Liu, Michael Tao","submitted_at":"2018-08-08T08:01:18Z","abstract_excerpt":"Many machine learning image classifiers are vulnerable to adversarial attacks, inputs with perturbations designed to intentionally trigger misclassification. Current adversarial methods directly alter pixel colors and evaluate against pixel norm-balls: pixel perturbations smaller than a specified magnitude, according to a measurement norm. This evaluation, however, has limited practical utility since perturbations in the pixel space do not correspond to underlying real-world phenomena of image formation that lead to them and has no security motivation attached. Pixels in natural images are mea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.02651","kind":"arxiv","version":2},"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":"1808.02651","created_at":"2026-05-17T23:53:51.061839+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.02651v2","created_at":"2026-05-17T23:53:51.061839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.02651","created_at":"2026-05-17T23:53:51.061839+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6OSRKNM4EOV","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6OSRKNM4EOVTMHF","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6OSRKNM","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.05418","citing_title":"Adversarial Objects Against LiDAR-Based Autonomous Driving Systems","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6OSRKNM4EOVTMHFVUEXNX5Q6N","json":"https://pith.science/pith/J6OSRKNM4EOVTMHFVUEXNX5Q6N.json","graph_json":"https://pith.science/api/pith-number/J6OSRKNM4EOVTMHFVUEXNX5Q6N/graph.json","events_json":"https://pith.science/api/pith-number/J6OSRKNM4EOVTMHFVUEXNX5Q6N/events.json","paper":"https://pith.science/paper/J6OSRKNM"},"agent_actions":{"view_html":"https://pith.science/pith/J6OSRKNM4EOVTMHFVUEXNX5Q6N","download_json":"https://pith.science/pith/J6OSRKNM4EOVTMHFVUEXNX5Q6N.json","view_paper":"https://pith.science/paper/J6OSRKNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.02651&json=true","fetch_graph":"https://pith.science/api/pith-number/J6OSRKNM4EOVTMHFVUEXNX5Q6N/graph.json","fetch_events":"https://pith.science/api/pith-number/J6OSRKNM4EOVTMHFVUEXNX5Q6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6OSRKNM4EOVTMHFVUEXNX5Q6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6OSRKNM4EOVTMHFVUEXNX5Q6N/action/storage_attestation","attest_author":"https://pith.science/pith/J6OSRKNM4EOVTMHFVUEXNX5Q6N/action/author_attestation","sign_citation":"https://pith.science/pith/J6OSRKNM4EOVTMHFVUEXNX5Q6N/action/citation_signature","submit_replication":"https://pith.science/pith/J6OSRKNM4EOVTMHFVUEXNX5Q6N/action/replication_record"}},"created_at":"2026-05-17T23:53:51.061839+00:00","updated_at":"2026-05-17T23:53:51.061839+00:00"}