{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RIG7WVN7535AXNZUFVFP4BVXOJ","short_pith_number":"pith:RIG7WVN7","schema_version":"1.0","canonical_sha256":"8a0dfb55bfeefa0bb7342d4afe06b7725cec1f18ec0109ada99b9c25c0b6728d","source":{"kind":"arxiv","id":"2409.03183","version":1},"attestation_state":"computed","paper":{"title":"Bypassing DARCY Defense: Indistinguishable Universal Adversarial Triggers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ben Niu, Jianbing Ni, Yuanyuan HE, Zuquan Peng","submitted_at":"2024-09-05T02:19:34Z","abstract_excerpt":"Neural networks (NN) classification models for Natural Language Processing (NLP) are vulnerable to the Universal Adversarial Triggers (UAT) attack that triggers a model to produce a specific prediction for any input. DARCY borrows the \"honeypot\" concept to bait multiple trapdoors, effectively detecting the adversarial examples generated by UAT. Unfortunately, we find a new UAT generation method, called IndisUAT, which produces triggers (i.e., tokens) and uses them to craft adversarial examples whose feature distribution is indistinguishable from that of the benign examples in a randomly-chosen"},"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":"2409.03183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T02:19:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f90396c9b8941610c9e9a33ff537c637c303d5407df4a8ed60424feccb9f56a6","abstract_canon_sha256":"0e4f08d9241ecbb8cb3912903b7abc00ec6c0a0d2fa4b2e4fcd4862d0207dcff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:27.217862Z","signature_b64":"LRI8h/1OEPKddsImw8jopkPBP4nZLl8OKJVBiefuIdfUwmY88v0Gjz/MezE7aIygxX3daR1cRc8qGdAEViuHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a0dfb55bfeefa0bb7342d4afe06b7725cec1f18ec0109ada99b9c25c0b6728d","last_reissued_at":"2026-07-05T09:03:27.217473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:27.217473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bypassing DARCY Defense: Indistinguishable Universal Adversarial Triggers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ben Niu, Jianbing Ni, Yuanyuan HE, Zuquan Peng","submitted_at":"2024-09-05T02:19:34Z","abstract_excerpt":"Neural networks (NN) classification models for Natural Language Processing (NLP) are vulnerable to the Universal Adversarial Triggers (UAT) attack that triggers a model to produce a specific prediction for any input. DARCY borrows the \"honeypot\" concept to bait multiple trapdoors, effectively detecting the adversarial examples generated by UAT. Unfortunately, we find a new UAT generation method, called IndisUAT, which produces triggers (i.e., tokens) and uses them to craft adversarial examples whose feature distribution is indistinguishable from that of the benign examples in a randomly-chosen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03183","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/2409.03183/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":"2409.03183","created_at":"2026-07-05T09:03:27.217528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03183v1","created_at":"2026-07-05T09:03:27.217528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03183","created_at":"2026-07-05T09:03:27.217528+00:00"},{"alias_kind":"pith_short_12","alias_value":"RIG7WVN7535A","created_at":"2026-07-05T09:03:27.217528+00:00"},{"alias_kind":"pith_short_16","alias_value":"RIG7WVN7535AXNZU","created_at":"2026-07-05T09:03:27.217528+00:00"},{"alias_kind":"pith_short_8","alias_value":"RIG7WVN7","created_at":"2026-07-05T09:03:27.217528+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/RIG7WVN7535AXNZUFVFP4BVXOJ","json":"https://pith.science/pith/RIG7WVN7535AXNZUFVFP4BVXOJ.json","graph_json":"https://pith.science/api/pith-number/RIG7WVN7535AXNZUFVFP4BVXOJ/graph.json","events_json":"https://pith.science/api/pith-number/RIG7WVN7535AXNZUFVFP4BVXOJ/events.json","paper":"https://pith.science/paper/RIG7WVN7"},"agent_actions":{"view_html":"https://pith.science/pith/RIG7WVN7535AXNZUFVFP4BVXOJ","download_json":"https://pith.science/pith/RIG7WVN7535AXNZUFVFP4BVXOJ.json","view_paper":"https://pith.science/paper/RIG7WVN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03183&json=true","fetch_graph":"https://pith.science/api/pith-number/RIG7WVN7535AXNZUFVFP4BVXOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/RIG7WVN7535AXNZUFVFP4BVXOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RIG7WVN7535AXNZUFVFP4BVXOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RIG7WVN7535AXNZUFVFP4BVXOJ/action/storage_attestation","attest_author":"https://pith.science/pith/RIG7WVN7535AXNZUFVFP4BVXOJ/action/author_attestation","sign_citation":"https://pith.science/pith/RIG7WVN7535AXNZUFVFP4BVXOJ/action/citation_signature","submit_replication":"https://pith.science/pith/RIG7WVN7535AXNZUFVFP4BVXOJ/action/replication_record"}},"created_at":"2026-07-05T09:03:27.217528+00:00","updated_at":"2026-07-05T09:03:27.217528+00:00"}