{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:M25ZFFGMDJR4LW3H6ZGYPXRZBD","short_pith_number":"pith:M25ZFFGM","canonical_record":{"source":{"id":"2504.14348","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T16:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"6872a7261676c9087a8aafea13ecbbd50b3cd85bd16dffe8609be37bd21df56f","abstract_canon_sha256":"119a1ee067fed402e8090150905252dc7b89f34ef967a5ad0deaafb1e87f8920"},"schema_version":"1.0"},"canonical_sha256":"66bb9294cc1a63c5db67f64d87de3908cef8da1c6e1e82aef42dfd38a1070acd","source":{"kind":"arxiv","id":"2504.14348","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14348","created_at":"2026-07-05T11:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14348v4","created_at":"2026-07-05T11:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14348","created_at":"2026-07-05T11:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"M25ZFFGMDJR4","created_at":"2026-07-05T11:44:04Z"},{"alias_kind":"pith_short_16","alias_value":"M25ZFFGMDJR4LW3H","created_at":"2026-07-05T11:44:04Z"},{"alias_kind":"pith_short_8","alias_value":"M25ZFFGM","created_at":"2026-07-05T11:44:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:M25ZFFGMDJR4LW3H6ZGYPXRZBD","target":"record","payload":{"canonical_record":{"source":{"id":"2504.14348","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T16:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"6872a7261676c9087a8aafea13ecbbd50b3cd85bd16dffe8609be37bd21df56f","abstract_canon_sha256":"119a1ee067fed402e8090150905252dc7b89f34ef967a5ad0deaafb1e87f8920"},"schema_version":"1.0"},"canonical_sha256":"66bb9294cc1a63c5db67f64d87de3908cef8da1c6e1e82aef42dfd38a1070acd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:04.388226Z","signature_b64":"JNl6+Of2Snapd1W1faYI2PtnQ8cjzNxXRj+nqfgn2LUiefwB3T4kJjtpNrzQ532h+boWYpF27VFeA+eHgNjZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66bb9294cc1a63c5db67f64d87de3908cef8da1c6e1e82aef42dfd38a1070acd","last_reissued_at":"2026-07-05T11:44:04.387695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:04.387695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.14348","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d3/dRTiQNYZksQ8zbQkGgoA59+OSGt0hvdKOFedzk1qGzfavehrkF4MU4Na5hcK64g6fQRZcSgcIsn2j7uwNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:50:20.152150Z"},"content_sha256":"c9ed499b5344814193b9bb5bae3070b75e91003bd52f33f24e46552875f061fe","schema_version":"1.0","event_id":"sha256:c9ed499b5344814193b9bb5bae3070b75e91003bd52f33f24e46552875f061fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:M25ZFFGMDJR4LW3H6ZGYPXRZBD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Manipulating Multimodal Agents via Cross-Modal Prompt Injection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aishan Liu, Le Wang, Mingchuan Zhang, Shengshan Hu, Siyuan Liang, Tianyuan Zhang, Xianglong Liu, Zonghao Ying","submitted_at":"2025-04-19T16:28:03Z","abstract_excerpt":"The emergence of multimodal large language models has redefined the agent paradigm by integrating language and vision modalities with external data sources, enabling agents to better interpret human instructions and execute increasingly complex tasks. However, in this paper, we identify a critical yet previously overlooked security vulnerability in multimodal agents: cross-modal prompt injection attacks. To exploit this vulnerability, we propose CrossInject, a novel attack framework in which attackers embed adversarial perturbations across multiple modalities to align with target malicious con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14348","kind":"arxiv","version":4},"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/2504.14348/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":"2026-07-05T11:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZYGuh7xQSv06duAUF6uMk2WdanZZPBeN8BiHMmBXNp/Ye/nyuzk0rDvbtLbHLacGbubwHpegyoMgyU8Ch8f0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:50:20.152971Z"},"content_sha256":"5cccabdfd00442661a9ac4c53cb0e5610fd512c237a75c571a6472948ef2c5c2","schema_version":"1.0","event_id":"sha256:5cccabdfd00442661a9ac4c53cb0e5610fd512c237a75c571a6472948ef2c5c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M25ZFFGMDJR4LW3H6ZGYPXRZBD/bundle.json","state_url":"https://pith.science/pith/M25ZFFGMDJR4LW3H6ZGYPXRZBD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M25ZFFGMDJR4LW3H6ZGYPXRZBD/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":"2026-08-03T17:50:20Z","links":{"resolver":"https://pith.science/pith/M25ZFFGMDJR4LW3H6ZGYPXRZBD","bundle":"https://pith.science/pith/M25ZFFGMDJR4LW3H6ZGYPXRZBD/bundle.json","state":"https://pith.science/pith/M25ZFFGMDJR4LW3H6ZGYPXRZBD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M25ZFFGMDJR4LW3H6ZGYPXRZBD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M25ZFFGMDJR4LW3H6ZGYPXRZBD","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":"119a1ee067fed402e8090150905252dc7b89f34ef967a5ad0deaafb1e87f8920","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T16:28:03Z","title_canon_sha256":"6872a7261676c9087a8aafea13ecbbd50b3cd85bd16dffe8609be37bd21df56f"},"schema_version":"1.0","source":{"id":"2504.14348","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14348","created_at":"2026-07-05T11:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14348v4","created_at":"2026-07-05T11:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14348","created_at":"2026-07-05T11:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"M25ZFFGMDJR4","created_at":"2026-07-05T11:44:04Z"},{"alias_kind":"pith_short_16","alias_value":"M25ZFFGMDJR4LW3H","created_at":"2026-07-05T11:44:04Z"},{"alias_kind":"pith_short_8","alias_value":"M25ZFFGM","created_at":"2026-07-05T11:44:04Z"}],"graph_snapshots":[{"event_id":"sha256:5cccabdfd00442661a9ac4c53cb0e5610fd512c237a75c571a6472948ef2c5c2","target":"graph","created_at":"2026-07-05T11:44:04Z","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/2504.14348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of multimodal large language models has redefined the agent paradigm by integrating language and vision modalities with external data sources, enabling agents to better interpret human instructions and execute increasingly complex tasks. However, in this paper, we identify a critical yet previously overlooked security vulnerability in multimodal agents: cross-modal prompt injection attacks. To exploit this vulnerability, we propose CrossInject, a novel attack framework in which attackers embed adversarial perturbations across multiple modalities to align with target malicious con","authors_text":"Aishan Liu, Le Wang, Mingchuan Zhang, Shengshan Hu, Siyuan Liang, Tianyuan Zhang, Xianglong Liu, Zonghao Ying","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T16:28:03Z","title":"Manipulating Multimodal Agents via Cross-Modal Prompt Injection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14348","kind":"arxiv","version":4},"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:c9ed499b5344814193b9bb5bae3070b75e91003bd52f33f24e46552875f061fe","target":"record","created_at":"2026-07-05T11:44:04Z","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":"119a1ee067fed402e8090150905252dc7b89f34ef967a5ad0deaafb1e87f8920","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-19T16:28:03Z","title_canon_sha256":"6872a7261676c9087a8aafea13ecbbd50b3cd85bd16dffe8609be37bd21df56f"},"schema_version":"1.0","source":{"id":"2504.14348","kind":"arxiv","version":4}},"canonical_sha256":"66bb9294cc1a63c5db67f64d87de3908cef8da1c6e1e82aef42dfd38a1070acd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66bb9294cc1a63c5db67f64d87de3908cef8da1c6e1e82aef42dfd38a1070acd","first_computed_at":"2026-07-05T11:44:04.387695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:04.387695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JNl6+Of2Snapd1W1faYI2PtnQ8cjzNxXRj+nqfgn2LUiefwB3T4kJjtpNrzQ532h+boWYpF27VFeA+eHgNjZDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:04.388226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14348","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9ed499b5344814193b9bb5bae3070b75e91003bd52f33f24e46552875f061fe","sha256:5cccabdfd00442661a9ac4c53cb0e5610fd512c237a75c571a6472948ef2c5c2"],"state_sha256":"4f19320473ccb37d376683251fb76dd3466fd4a4f25b54c8a1218516a50f3d56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D2WMTwFXpLSbZAM/COYReDvCSAzubvP7vDVsrHaNXYstQTmRpOha7n4CvZiocN2odxuz6GNaiWIt3Ff3fNe9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:50:20.158595Z","bundle_sha256":"4393ca6383b2fe44b155684393cdab52e6c741ad74cdbd4026712ed641b6bc25"}}