{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z7FRZABKYLN7F3ZM5YATAKWTGJ","short_pith_number":"pith:Z7FRZABK","schema_version":"1.0","canonical_sha256":"cfcb1c802ac2dbf2ef2cee01302ad33245ed61499a12496cbc8de97dfef11c1f","source":{"kind":"arxiv","id":"2505.15332","version":1},"attestation_state":"computed","paper":{"title":"Towards Zero-Shot Differential Morphing Attack Detection with Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hailin Li, Raghavendra Ramachandra, Ria Shekhawat, Sushma Venkatesh","submitted_at":"2025-05-21T10:05:19Z","abstract_excerpt":"Leveraging the power of multimodal large language models (LLMs) offers a promising approach to enhancing the accuracy and interpretability of morphing attack detection (MAD), especially in real-world biometric applications. This work introduces the use of LLMs for differential morphing attack detection (D-MAD). To the best of our knowledge, this is the first study to employ multimodal LLMs to D-MAD using real biometric data. To effectively utilize these models, we design Chain-of-Thought (CoT)-based prompts to reduce failure-to-answer rates and enhance the reasoning behind decisions. Our contr"},"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":"2505.15332","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-21T10:05:19Z","cross_cats_sorted":[],"title_canon_sha256":"f86f4cd09d71d43ff57183681efe54c9accb6ff9d465f040c9553237c03358d9","abstract_canon_sha256":"c88e930913145f8a3f88fe63a4133be34100e6120f1478f0428e54e29a24af95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:43.888665Z","signature_b64":"MOV1BVHBMK6b8RzreTpncpnTMGjoYG5M5Yi1i/l5zoZGK7cUoLHHJoyzKX9Ca7JrceEXQDkA/IGj9kcu9z8VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfcb1c802ac2dbf2ef2cee01302ad33245ed61499a12496cbc8de97dfef11c1f","last_reissued_at":"2026-07-05T11:06:43.888196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:43.888196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Zero-Shot Differential Morphing Attack Detection with Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hailin Li, Raghavendra Ramachandra, Ria Shekhawat, Sushma Venkatesh","submitted_at":"2025-05-21T10:05:19Z","abstract_excerpt":"Leveraging the power of multimodal large language models (LLMs) offers a promising approach to enhancing the accuracy and interpretability of morphing attack detection (MAD), especially in real-world biometric applications. This work introduces the use of LLMs for differential morphing attack detection (D-MAD). To the best of our knowledge, this is the first study to employ multimodal LLMs to D-MAD using real biometric data. To effectively utilize these models, we design Chain-of-Thought (CoT)-based prompts to reduce failure-to-answer rates and enhance the reasoning behind decisions. Our contr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15332","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/2505.15332/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":"2505.15332","created_at":"2026-07-05T11:06:43.888253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15332v1","created_at":"2026-07-05T11:06:43.888253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15332","created_at":"2026-07-05T11:06:43.888253+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7FRZABKYLN7","created_at":"2026-07-05T11:06:43.888253+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7FRZABKYLN7F3ZM","created_at":"2026-07-05T11:06:43.888253+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7FRZABK","created_at":"2026-07-05T11:06:43.888253+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17961","citing_title":"DifFoundMAD: Foundation Models meet Differential Morphing Attack Detection","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7FRZABKYLN7F3ZM5YATAKWTGJ","json":"https://pith.science/pith/Z7FRZABKYLN7F3ZM5YATAKWTGJ.json","graph_json":"https://pith.science/api/pith-number/Z7FRZABKYLN7F3ZM5YATAKWTGJ/graph.json","events_json":"https://pith.science/api/pith-number/Z7FRZABKYLN7F3ZM5YATAKWTGJ/events.json","paper":"https://pith.science/paper/Z7FRZABK"},"agent_actions":{"view_html":"https://pith.science/pith/Z7FRZABKYLN7F3ZM5YATAKWTGJ","download_json":"https://pith.science/pith/Z7FRZABKYLN7F3ZM5YATAKWTGJ.json","view_paper":"https://pith.science/paper/Z7FRZABK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15332&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7FRZABKYLN7F3ZM5YATAKWTGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7FRZABKYLN7F3ZM5YATAKWTGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7FRZABKYLN7F3ZM5YATAKWTGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7FRZABKYLN7F3ZM5YATAKWTGJ/action/storage_attestation","attest_author":"https://pith.science/pith/Z7FRZABKYLN7F3ZM5YATAKWTGJ/action/author_attestation","sign_citation":"https://pith.science/pith/Z7FRZABKYLN7F3ZM5YATAKWTGJ/action/citation_signature","submit_replication":"https://pith.science/pith/Z7FRZABKYLN7F3ZM5YATAKWTGJ/action/replication_record"}},"created_at":"2026-07-05T11:06:43.888253+00:00","updated_at":"2026-07-05T11:06:43.888253+00:00"}