{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FZE7HAQSRREW3GUHSJYAICAHDL","short_pith_number":"pith:FZE7HAQS","schema_version":"1.0","canonical_sha256":"2e49f382128c496d9a8792700408071afecaa7c4ca00f8d2b9e06208c4ea0120","source":{"kind":"arxiv","id":"1908.09364","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Edit Attacks for Tree Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Paa{\\ss}en","submitted_at":"2019-08-25T17:20:15Z","abstract_excerpt":"Many machine learning models can be attacked with adversarial examples, i.e. inputs close to correctly classified examples that are classified incorrectly. However, most research on adversarial attacks to date is limited to vectorial data, in particular image data. In this contribution, we extend the field by introducing adversarial edit attacks for tree-structured data with potential applications in medicine and automated program analysis. Our approach solely relies on the tree edit distance and a logarithmic number of black-box queries to the attacked classifier without any need for gradient"},"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":"1908.09364","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-25T17:20:15Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"eb2d89bb3a5daf70752ece4573a4c8a92bda076c2d9af5d44aafa66d7811c3b0","abstract_canon_sha256":"21bbcc2030aeb6f388bc340164904c244dab2746a8a9b5e4f465bd49094b7f60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:09.911493Z","signature_b64":"1BhUMFfBj8rKTvc65l4ACGT4ojFBqcWHobdb6bKxPIMbKaQ2ob3oW9nFeRuFuEhP7zXGuV3rjBijzt+MqU50DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e49f382128c496d9a8792700408071afecaa7c4ca00f8d2b9e06208c4ea0120","last_reissued_at":"2026-07-05T00:18:09.911153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:09.911153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Edit Attacks for Tree Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Paa{\\ss}en","submitted_at":"2019-08-25T17:20:15Z","abstract_excerpt":"Many machine learning models can be attacked with adversarial examples, i.e. inputs close to correctly classified examples that are classified incorrectly. However, most research on adversarial attacks to date is limited to vectorial data, in particular image data. In this contribution, we extend the field by introducing adversarial edit attacks for tree-structured data with potential applications in medicine and automated program analysis. Our approach solely relies on the tree edit distance and a logarithmic number of black-box queries to the attacked classifier without any need for gradient"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09364","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.09364/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":"1908.09364","created_at":"2026-07-05T00:18:09.911207+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09364v2","created_at":"2026-07-05T00:18:09.911207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09364","created_at":"2026-07-05T00:18:09.911207+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZE7HAQSRREW","created_at":"2026-07-05T00:18:09.911207+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZE7HAQSRREW3GUH","created_at":"2026-07-05T00:18:09.911207+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZE7HAQS","created_at":"2026-07-05T00:18:09.911207+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/FZE7HAQSRREW3GUHSJYAICAHDL","json":"https://pith.science/pith/FZE7HAQSRREW3GUHSJYAICAHDL.json","graph_json":"https://pith.science/api/pith-number/FZE7HAQSRREW3GUHSJYAICAHDL/graph.json","events_json":"https://pith.science/api/pith-number/FZE7HAQSRREW3GUHSJYAICAHDL/events.json","paper":"https://pith.science/paper/FZE7HAQS"},"agent_actions":{"view_html":"https://pith.science/pith/FZE7HAQSRREW3GUHSJYAICAHDL","download_json":"https://pith.science/pith/FZE7HAQSRREW3GUHSJYAICAHDL.json","view_paper":"https://pith.science/paper/FZE7HAQS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09364&json=true","fetch_graph":"https://pith.science/api/pith-number/FZE7HAQSRREW3GUHSJYAICAHDL/graph.json","fetch_events":"https://pith.science/api/pith-number/FZE7HAQSRREW3GUHSJYAICAHDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZE7HAQSRREW3GUHSJYAICAHDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZE7HAQSRREW3GUHSJYAICAHDL/action/storage_attestation","attest_author":"https://pith.science/pith/FZE7HAQSRREW3GUHSJYAICAHDL/action/author_attestation","sign_citation":"https://pith.science/pith/FZE7HAQSRREW3GUHSJYAICAHDL/action/citation_signature","submit_replication":"https://pith.science/pith/FZE7HAQSRREW3GUHSJYAICAHDL/action/replication_record"}},"created_at":"2026-07-05T00:18:09.911207+00:00","updated_at":"2026-07-05T00:18:09.911207+00:00"}