{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GXPW7FZWT3AJZARMSMILGZCCAS","short_pith_number":"pith:GXPW7FZW","schema_version":"1.0","canonical_sha256":"35df6f97369ec09c822c9310b364420489bae34498fb5221a17a8ae3cdfa18d5","source":{"kind":"arxiv","id":"1909.08072","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Attacks and Defenses in Images, Graphs and Text: A Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anil K. Jain, Debayan Deb, Han Xu, Haochen Liu, Hui Liu, Jiliang Tang, Yao Ma","submitted_at":"2019-09-17T20:07:23Z","abstract_excerpt":"Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the st"},"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":"1909.08072","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-17T20:07:23Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"04113d5b63f8c70f41c533108715d51eaf6c4f62415d44460bd1ec0c0f72cbc3","abstract_canon_sha256":"93cbf3e56f701828e9cc424c6cba2775c5ab23425136f4419623ee62755a2802"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:54.697512Z","signature_b64":"SuLIbS7l7pFkcUXqcs/uBE3GcYRkrNT6drwJOc5BJtvmhPkbTWBNtq4Vdw9EUtKNubaBD7vZ90PikfLKaYTtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35df6f97369ec09c822c9310b364420489bae34498fb5221a17a8ae3cdfa18d5","last_reissued_at":"2026-07-05T00:10:54.697138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:54.697138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Attacks and Defenses in Images, Graphs and Text: A Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anil K. Jain, Debayan Deb, Han Xu, Haochen Liu, Hui Liu, Jiliang Tang, Yao Ma","submitted_at":"2019-09-17T20:07:23Z","abstract_excerpt":"Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.08072","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/1909.08072/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":"1909.08072","created_at":"2026-07-05T00:10:54.697194+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.08072v2","created_at":"2026-07-05T00:10:54.697194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.08072","created_at":"2026-07-05T00:10:54.697194+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXPW7FZWT3AJ","created_at":"2026-07-05T00:10:54.697194+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXPW7FZWT3AJZARM","created_at":"2026-07-05T00:10:54.697194+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXPW7FZW","created_at":"2026-07-05T00:10:54.697194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2209.07858","citing_title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXPW7FZWT3AJZARMSMILGZCCAS","json":"https://pith.science/pith/GXPW7FZWT3AJZARMSMILGZCCAS.json","graph_json":"https://pith.science/api/pith-number/GXPW7FZWT3AJZARMSMILGZCCAS/graph.json","events_json":"https://pith.science/api/pith-number/GXPW7FZWT3AJZARMSMILGZCCAS/events.json","paper":"https://pith.science/paper/GXPW7FZW"},"agent_actions":{"view_html":"https://pith.science/pith/GXPW7FZWT3AJZARMSMILGZCCAS","download_json":"https://pith.science/pith/GXPW7FZWT3AJZARMSMILGZCCAS.json","view_paper":"https://pith.science/paper/GXPW7FZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.08072&json=true","fetch_graph":"https://pith.science/api/pith-number/GXPW7FZWT3AJZARMSMILGZCCAS/graph.json","fetch_events":"https://pith.science/api/pith-number/GXPW7FZWT3AJZARMSMILGZCCAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXPW7FZWT3AJZARMSMILGZCCAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXPW7FZWT3AJZARMSMILGZCCAS/action/storage_attestation","attest_author":"https://pith.science/pith/GXPW7FZWT3AJZARMSMILGZCCAS/action/author_attestation","sign_citation":"https://pith.science/pith/GXPW7FZWT3AJZARMSMILGZCCAS/action/citation_signature","submit_replication":"https://pith.science/pith/GXPW7FZWT3AJZARMSMILGZCCAS/action/replication_record"}},"created_at":"2026-07-05T00:10:54.697194+00:00","updated_at":"2026-07-05T00:10:54.697194+00:00"}