{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WIGWEJNKKBWIXGR72KF7NRTML5","short_pith_number":"pith:WIGWEJNK","schema_version":"1.0","canonical_sha256":"b20d6225aa506c8b9a3fd28bf6c66c5f6bdc3edd8b71442abb612b63cd167501","source":{"kind":"arxiv","id":"1707.05373","version":1},"attestation_state":"computed","paper":{"title":"Houdini: Fooling Deep Structured Prediction Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Joseph Keshet, Moustapha Cisse, Natalia Neverova, Yossi Adi","submitted_at":"2017-07-17T19:11:08Z","abstract_excerpt":"Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines. So far, most existing methods only work for classification and are not designed to alter the true performance measure of the problem at hand. We introduce a novel flexible approach named Houdini for generating adversarial examples specifically tailored for the final performance measure of the task considered, be it combinatorial and non-decomposable. We successfully apply Houdini to a range of applications such as speech recognition, pose estimation and semantic segmentation. In"},"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":"1707.05373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-17T19:11:08Z","cross_cats_sorted":["cs.AI","cs.CR","cs.CV","cs.LG"],"title_canon_sha256":"f3a47ed27c651d35e714472520106c29e1e3ad9446792531f860acb00407043f","abstract_canon_sha256":"ec8942b8e877cc23487a31d16b460d89148521a1f0b67d55840010398dbcccf9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:02.540957Z","signature_b64":"IsaMezxhmHA1GrSch9Svjx+B5xf1myp7kYH5fmvRYO+rsJ2D/73062zeICC/+LutittYdqJy5sKuhC3JW1k4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b20d6225aa506c8b9a3fd28bf6c66c5f6bdc3edd8b71442abb612b63cd167501","last_reissued_at":"2026-05-18T00:40:02.540533Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:02.540533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Houdini: Fooling Deep Structured Prediction Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Joseph Keshet, Moustapha Cisse, Natalia Neverova, Yossi Adi","submitted_at":"2017-07-17T19:11:08Z","abstract_excerpt":"Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines. So far, most existing methods only work for classification and are not designed to alter the true performance measure of the problem at hand. We introduce a novel flexible approach named Houdini for generating adversarial examples specifically tailored for the final performance measure of the task considered, be it combinatorial and non-decomposable. We successfully apply Houdini to a range of applications such as speech recognition, pose estimation and semantic segmentation. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.05373","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":"1707.05373","created_at":"2026-05-18T00:40:02.540603+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.05373v1","created_at":"2026-05-18T00:40:02.540603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.05373","created_at":"2026-05-18T00:40:02.540603+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIGWEJNKKBWI","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIGWEJNKKBWIXGR7","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIGWEJNK","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.00374","citing_title":"Fooling a Real Car with Adversarial Traffic Signs","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WIGWEJNKKBWIXGR72KF7NRTML5","json":"https://pith.science/pith/WIGWEJNKKBWIXGR72KF7NRTML5.json","graph_json":"https://pith.science/api/pith-number/WIGWEJNKKBWIXGR72KF7NRTML5/graph.json","events_json":"https://pith.science/api/pith-number/WIGWEJNKKBWIXGR72KF7NRTML5/events.json","paper":"https://pith.science/paper/WIGWEJNK"},"agent_actions":{"view_html":"https://pith.science/pith/WIGWEJNKKBWIXGR72KF7NRTML5","download_json":"https://pith.science/pith/WIGWEJNKKBWIXGR72KF7NRTML5.json","view_paper":"https://pith.science/paper/WIGWEJNK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.05373&json=true","fetch_graph":"https://pith.science/api/pith-number/WIGWEJNKKBWIXGR72KF7NRTML5/graph.json","fetch_events":"https://pith.science/api/pith-number/WIGWEJNKKBWIXGR72KF7NRTML5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIGWEJNKKBWIXGR72KF7NRTML5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIGWEJNKKBWIXGR72KF7NRTML5/action/storage_attestation","attest_author":"https://pith.science/pith/WIGWEJNKKBWIXGR72KF7NRTML5/action/author_attestation","sign_citation":"https://pith.science/pith/WIGWEJNKKBWIXGR72KF7NRTML5/action/citation_signature","submit_replication":"https://pith.science/pith/WIGWEJNKKBWIXGR72KF7NRTML5/action/replication_record"}},"created_at":"2026-05-18T00:40:02.540603+00:00","updated_at":"2026-05-18T00:40:02.540603+00:00"}