{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZSXMT5WRC7FXJP3NH7OFOU3BOP","short_pith_number":"pith:ZSXMT5WR","schema_version":"1.0","canonical_sha256":"ccaec9f6d117cb74bf6d3fdc57536173e3f3715bd2895e7a3c6ac993b61a57c7","source":{"kind":"arxiv","id":"2404.05639","version":1},"attestation_state":"computed","paper":{"title":"Investigating the Impact of Quantization on Adversarial Robustness","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Chen Tang, Jiacheng Jiang, Qun Li, Yuan Meng, Zhi Wang","submitted_at":"2024-04-08T16:20:15Z","abstract_excerpt":"Quantization is a promising technique for reducing the bit-width of deep models to improve their runtime performance and storage efficiency, and thus becomes a fundamental step for deployment. In real-world scenarios, quantized models are often faced with adversarial attacks which cause the model to make incorrect inferences by introducing slight perturbations. However, recent studies have paid less attention to the impact of quantization on the model robustness. More surprisingly, existing studies on this topic even present inconsistent conclusions, which prompted our in-depth investigation. "},"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":"2404.05639","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-08T16:20:15Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"015fc346b2d564c6e6a1e518155530620dbc2965824ad7c74a5f3a8703a02182","abstract_canon_sha256":"72a02afa0c6e8a0cce5e39ccace8c0f67a3ab0ed3dd44b3a0dd84a390628c72b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:43.591081Z","signature_b64":"wsd9g+Fds5071bwXuKWSAozyXEJk1CMEeGs//355T9KJlzSPc+cLLrfg6cdrmM+wKRRaty7AIrWyWeRkfjnKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccaec9f6d117cb74bf6d3fdc57536173e3f3715bd2895e7a3c6ac993b61a57c7","last_reissued_at":"2026-07-05T08:05:43.590744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:43.590744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating the Impact of Quantization on Adversarial Robustness","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Chen Tang, Jiacheng Jiang, Qun Li, Yuan Meng, Zhi Wang","submitted_at":"2024-04-08T16:20:15Z","abstract_excerpt":"Quantization is a promising technique for reducing the bit-width of deep models to improve their runtime performance and storage efficiency, and thus becomes a fundamental step for deployment. In real-world scenarios, quantized models are often faced with adversarial attacks which cause the model to make incorrect inferences by introducing slight perturbations. However, recent studies have paid less attention to the impact of quantization on the model robustness. More surprisingly, existing studies on this topic even present inconsistent conclusions, which prompted our in-depth investigation. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05639","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.05639/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":"2404.05639","created_at":"2026-07-05T08:05:43.590799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05639v1","created_at":"2026-07-05T08:05:43.590799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05639","created_at":"2026-07-05T08:05:43.590799+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSXMT5WRC7FX","created_at":"2026-07-05T08:05:43.590799+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSXMT5WRC7FXJP3N","created_at":"2026-07-05T08:05:43.590799+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSXMT5WR","created_at":"2026-07-05T08:05:43.590799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15246","citing_title":"Exploring the Robustness and Transferability of Patch-Based Adversarial Attacks in Quantized Neural Networks","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSXMT5WRC7FXJP3NH7OFOU3BOP","json":"https://pith.science/pith/ZSXMT5WRC7FXJP3NH7OFOU3BOP.json","graph_json":"https://pith.science/api/pith-number/ZSXMT5WRC7FXJP3NH7OFOU3BOP/graph.json","events_json":"https://pith.science/api/pith-number/ZSXMT5WRC7FXJP3NH7OFOU3BOP/events.json","paper":"https://pith.science/paper/ZSXMT5WR"},"agent_actions":{"view_html":"https://pith.science/pith/ZSXMT5WRC7FXJP3NH7OFOU3BOP","download_json":"https://pith.science/pith/ZSXMT5WRC7FXJP3NH7OFOU3BOP.json","view_paper":"https://pith.science/paper/ZSXMT5WR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05639&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSXMT5WRC7FXJP3NH7OFOU3BOP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSXMT5WRC7FXJP3NH7OFOU3BOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSXMT5WRC7FXJP3NH7OFOU3BOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSXMT5WRC7FXJP3NH7OFOU3BOP/action/storage_attestation","attest_author":"https://pith.science/pith/ZSXMT5WRC7FXJP3NH7OFOU3BOP/action/author_attestation","sign_citation":"https://pith.science/pith/ZSXMT5WRC7FXJP3NH7OFOU3BOP/action/citation_signature","submit_replication":"https://pith.science/pith/ZSXMT5WRC7FXJP3NH7OFOU3BOP/action/replication_record"}},"created_at":"2026-07-05T08:05:43.590799+00:00","updated_at":"2026-07-05T08:05:43.590799+00:00"}