{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WGXSO7YP5FZF6DWPO56PC2KMA6","short_pith_number":"pith:WGXSO7YP","schema_version":"1.0","canonical_sha256":"b1af277f0fe9725f0ecf777cf1694c0795558e211f790c63d625c61730b06af4","source":{"kind":"arxiv","id":"2409.01249","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ambra Demontis, Battista Biggio, Fabio Roli, Giorgio Giacinto, Giorgio Piras, Maura Pintor","submitted_at":"2024-09-02T13:34:01Z","abstract_excerpt":"Recent work has proposed neural network pruning techniques to reduce the size of a network while preserving robustness against adversarial examples, i.e., well-crafted inputs inducing a misclassification. These methods, which we refer to as adversarial pruning methods, involve complex and articulated designs, making it difficult to analyze the differences and establish a fair and accurate comparison. In this work, we overcome these issues by surveying current adversarial pruning methods and proposing a novel taxonomy to categorize them based on two main dimensions: the pipeline, defining when "},"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":"2409.01249","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-02T13:34:01Z","cross_cats_sorted":["cs.CR","cs.CV"],"title_canon_sha256":"a1c3c5ed14ce154c54b9f30038f54b73c7112fae2b137fdc1a2533894575dd85","abstract_canon_sha256":"8ea94dbcbda50f20d995fd7d6fc06ff7670dd2b8a5c894673f8200de161f6897"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:19.922871Z","signature_b64":"he+/S76c0WcflDPsX/zeAkN2sMEPLkxG2vCRm4qz4gbygLWd5TATqAiL+Pcj8frmx3gQtJ2clqsAKcmJGhHnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1af277f0fe9725f0ecf777cf1694c0795558e211f790c63d625c61730b06af4","last_reissued_at":"2026-07-05T11:12:19.922294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:19.922294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ambra Demontis, Battista Biggio, Fabio Roli, Giorgio Giacinto, Giorgio Piras, Maura Pintor","submitted_at":"2024-09-02T13:34:01Z","abstract_excerpt":"Recent work has proposed neural network pruning techniques to reduce the size of a network while preserving robustness against adversarial examples, i.e., well-crafted inputs inducing a misclassification. These methods, which we refer to as adversarial pruning methods, involve complex and articulated designs, making it difficult to analyze the differences and establish a fair and accurate comparison. In this work, we overcome these issues by surveying current adversarial pruning methods and proposing a novel taxonomy to categorize them based on two main dimensions: the pipeline, defining when "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01249","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/2409.01249/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":"2409.01249","created_at":"2026-07-05T11:12:19.922366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01249v2","created_at":"2026-07-05T11:12:19.922366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01249","created_at":"2026-07-05T11:12:19.922366+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGXSO7YP5FZF","created_at":"2026-07-05T11:12:19.922366+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGXSO7YP5FZF6DWP","created_at":"2026-07-05T11:12:19.922366+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGXSO7YP","created_at":"2026-07-05T11:12:19.922366+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/WGXSO7YP5FZF6DWPO56PC2KMA6","json":"https://pith.science/pith/WGXSO7YP5FZF6DWPO56PC2KMA6.json","graph_json":"https://pith.science/api/pith-number/WGXSO7YP5FZF6DWPO56PC2KMA6/graph.json","events_json":"https://pith.science/api/pith-number/WGXSO7YP5FZF6DWPO56PC2KMA6/events.json","paper":"https://pith.science/paper/WGXSO7YP"},"agent_actions":{"view_html":"https://pith.science/pith/WGXSO7YP5FZF6DWPO56PC2KMA6","download_json":"https://pith.science/pith/WGXSO7YP5FZF6DWPO56PC2KMA6.json","view_paper":"https://pith.science/paper/WGXSO7YP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01249&json=true","fetch_graph":"https://pith.science/api/pith-number/WGXSO7YP5FZF6DWPO56PC2KMA6/graph.json","fetch_events":"https://pith.science/api/pith-number/WGXSO7YP5FZF6DWPO56PC2KMA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGXSO7YP5FZF6DWPO56PC2KMA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGXSO7YP5FZF6DWPO56PC2KMA6/action/storage_attestation","attest_author":"https://pith.science/pith/WGXSO7YP5FZF6DWPO56PC2KMA6/action/author_attestation","sign_citation":"https://pith.science/pith/WGXSO7YP5FZF6DWPO56PC2KMA6/action/citation_signature","submit_replication":"https://pith.science/pith/WGXSO7YP5FZF6DWPO56PC2KMA6/action/replication_record"}},"created_at":"2026-07-05T11:12:19.922366+00:00","updated_at":"2026-07-05T11:12:19.922366+00:00"}