{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:I46U346XX3QOMNAR6HDDSCJCGF","short_pith_number":"pith:I46U346X","canonical_record":{"source":{"id":"2409.19232","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-28T04:37:09Z","cross_cats_sorted":[],"title_canon_sha256":"fc7465212d32cc9461a08fb80cde0f9da7c03f2eaa756b43f83308c1d14b9f80","abstract_canon_sha256":"618d128a9ba607c0925377b80bbe8ca9488f293737a1856ebba96db814fe2c85"},"schema_version":"1.0"},"canonical_sha256":"473d4df3d7bee0e63411f1c6390922316dec5c0febfeca29ba3ca67a179c54f3","source":{"kind":"arxiv","id":"2409.19232","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19232","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19232v1","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19232","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"pith_short_12","alias_value":"I46U346XX3QO","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"pith_short_16","alias_value":"I46U346XX3QOMNAR","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"pith_short_8","alias_value":"I46U346X","created_at":"2026-07-05T09:13:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:I46U346XX3QOMNAR6HDDSCJCGF","target":"record","payload":{"canonical_record":{"source":{"id":"2409.19232","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-28T04:37:09Z","cross_cats_sorted":[],"title_canon_sha256":"fc7465212d32cc9461a08fb80cde0f9da7c03f2eaa756b43f83308c1d14b9f80","abstract_canon_sha256":"618d128a9ba607c0925377b80bbe8ca9488f293737a1856ebba96db814fe2c85"},"schema_version":"1.0"},"canonical_sha256":"473d4df3d7bee0e63411f1c6390922316dec5c0febfeca29ba3ca67a179c54f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:12.543216Z","signature_b64":"mPwHraXk0wtgRxZJIocM9f9WQqI1q908d77UpRq1knOBpja7VmX+a2KCUUo50MAXBkjmJ88/LM4PT6idTZo9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"473d4df3d7bee0e63411f1c6390922316dec5c0febfeca29ba3ca67a179c54f3","last_reissued_at":"2026-07-05T09:13:12.542747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:12.542747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.19232","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:13:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hYnSBnYlC01qKpb3KXrCh/lCEmCeGVgNHT8eWWmLTfbl9ATfOMx+6DSqwjBG/IUTwMfDXTsWiQ8i7joTsacHCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:52:20.524394Z"},"content_sha256":"d709e4e69669188688339cd50845f3e6c874881152ae1218d5b768d51c7c6f93","schema_version":"1.0","event_id":"sha256:d709e4e69669188688339cd50845f3e6c874881152ae1218d5b768d51c7c6f93"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:I46U346XX3QOMNAR6HDDSCJCGF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TrojVLM: Backdoor Attack Against Vision Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Chen, Haibin Ling, Lu Pang, Tengfei Ma, Weimin Lyu","submitted_at":"2024-09-28T04:37:09Z","abstract_excerpt":"The emergence of Vision Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to produce detailed text descriptions based on visual inputs, yet it introduces new security vulnerabilities. Unlike prior work that centered on single modalities or classification tasks, this study introduces TrojVLM, the first exploration of backdoor attacks aimed at VLMs engaged in complex image-to-text generation. Specifically, TrojVLM inserts predetermined target text into output text when encountering poisoned images. Moreover, a novel semantic pres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19232","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/2409.19232/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:13:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"donRtx/aQoU+nuCjx6xyPmqbrTxTKtnHddgir0T9fRcJAskIWPA0/rry5qg86hB5n9tkw6iGjKfpMNZQ7f2+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:52:20.524912Z"},"content_sha256":"b865020de7dcf3df13d83271ef94cac3aa49e215290f6e3835e446c7eb957917","schema_version":"1.0","event_id":"sha256:b865020de7dcf3df13d83271ef94cac3aa49e215290f6e3835e446c7eb957917"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I46U346XX3QOMNAR6HDDSCJCGF/bundle.json","state_url":"https://pith.science/pith/I46U346XX3QOMNAR6HDDSCJCGF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I46U346XX3QOMNAR6HDDSCJCGF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T09:52:20Z","links":{"resolver":"https://pith.science/pith/I46U346XX3QOMNAR6HDDSCJCGF","bundle":"https://pith.science/pith/I46U346XX3QOMNAR6HDDSCJCGF/bundle.json","state":"https://pith.science/pith/I46U346XX3QOMNAR6HDDSCJCGF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I46U346XX3QOMNAR6HDDSCJCGF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I46U346XX3QOMNAR6HDDSCJCGF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"618d128a9ba607c0925377b80bbe8ca9488f293737a1856ebba96db814fe2c85","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-28T04:37:09Z","title_canon_sha256":"fc7465212d32cc9461a08fb80cde0f9da7c03f2eaa756b43f83308c1d14b9f80"},"schema_version":"1.0","source":{"id":"2409.19232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.19232","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"arxiv_version","alias_value":"2409.19232v1","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19232","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"pith_short_12","alias_value":"I46U346XX3QO","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"pith_short_16","alias_value":"I46U346XX3QOMNAR","created_at":"2026-07-05T09:13:12Z"},{"alias_kind":"pith_short_8","alias_value":"I46U346X","created_at":"2026-07-05T09:13:12Z"}],"graph_snapshots":[{"event_id":"sha256:b865020de7dcf3df13d83271ef94cac3aa49e215290f6e3835e446c7eb957917","target":"graph","created_at":"2026-07-05T09:13:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.19232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of Vision Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to produce detailed text descriptions based on visual inputs, yet it introduces new security vulnerabilities. Unlike prior work that centered on single modalities or classification tasks, this study introduces TrojVLM, the first exploration of backdoor attacks aimed at VLMs engaged in complex image-to-text generation. Specifically, TrojVLM inserts predetermined target text into output text when encountering poisoned images. Moreover, a novel semantic pres","authors_text":"Chao Chen, Haibin Ling, Lu Pang, Tengfei Ma, Weimin Lyu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-28T04:37:09Z","title":"TrojVLM: Backdoor Attack Against Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19232","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d709e4e69669188688339cd50845f3e6c874881152ae1218d5b768d51c7c6f93","target":"record","created_at":"2026-07-05T09:13:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"618d128a9ba607c0925377b80bbe8ca9488f293737a1856ebba96db814fe2c85","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-28T04:37:09Z","title_canon_sha256":"fc7465212d32cc9461a08fb80cde0f9da7c03f2eaa756b43f83308c1d14b9f80"},"schema_version":"1.0","source":{"id":"2409.19232","kind":"arxiv","version":1}},"canonical_sha256":"473d4df3d7bee0e63411f1c6390922316dec5c0febfeca29ba3ca67a179c54f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"473d4df3d7bee0e63411f1c6390922316dec5c0febfeca29ba3ca67a179c54f3","first_computed_at":"2026-07-05T09:13:12.542747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:12.542747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mPwHraXk0wtgRxZJIocM9f9WQqI1q908d77UpRq1knOBpja7VmX+a2KCUUo50MAXBkjmJ88/LM4PT6idTZo9BA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:12.543216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.19232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d709e4e69669188688339cd50845f3e6c874881152ae1218d5b768d51c7c6f93","sha256:b865020de7dcf3df13d83271ef94cac3aa49e215290f6e3835e446c7eb957917"],"state_sha256":"c978e54f5614a2260b4166090c0ff3b7b01887b470dafe33298009deec1981ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Cu7XGudAw1g6xAII79Hr1CVh0zE1FFb6QHO7TXv3yL0obNR1659XExsD3AoZyCzlZhK1fwo5uyHogKvecWZAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:52:20.531221Z","bundle_sha256":"f71429d36a13460333464eb3e4ac9b5573f1e2f4c51d6af27fc4d252935135c6"}}