{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AKF5Z5IPEYDRDS2MTERZNUZCLG","short_pith_number":"pith:AKF5Z5IP","canonical_record":{"source":{"id":"2410.08776","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-10-11T12:49:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c350f87c62ee102bb673df9c6360879461da634c0515ad743e20b15b7cbf5de","abstract_canon_sha256":"341b9d3ead9a6e6de7fc833f65de47bb669eff3324b3d5e0a63fec47320af988"},"schema_version":"1.0"},"canonical_sha256":"028bdcf50f260711cb4c992396d3225981613ab57121896f59da0373f5001b14","source":{"kind":"arxiv","id":"2410.08776","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08776","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08776v2","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08776","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_12","alias_value":"AKF5Z5IPEYDR","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_16","alias_value":"AKF5Z5IPEYDRDS2M","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_8","alias_value":"AKF5Z5IP","created_at":"2026-07-05T09:20:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AKF5Z5IPEYDRDS2MTERZNUZCLG","target":"record","payload":{"canonical_record":{"source":{"id":"2410.08776","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-10-11T12:49:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c350f87c62ee102bb673df9c6360879461da634c0515ad743e20b15b7cbf5de","abstract_canon_sha256":"341b9d3ead9a6e6de7fc833f65de47bb669eff3324b3d5e0a63fec47320af988"},"schema_version":"1.0"},"canonical_sha256":"028bdcf50f260711cb4c992396d3225981613ab57121896f59da0373f5001b14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:04.930282Z","signature_b64":"4EiEVM5I0WrhAD5obvXflfyas8N9rrca7MO2UkCFAQeF+22sAFAus1kox0rs/Ipywru5XYooLYN3NREV3OsiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"028bdcf50f260711cb4c992396d3225981613ab57121896f59da0373f5001b14","last_reissued_at":"2026-07-05T09:20:04.929851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:04.929851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.08776","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:20:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wkgDA+iM1nIWd3ns8YA+cM6zf60eiOpWIFIpypA5gV26ROjGcheJYdZN2caQnDzIvVFxiY3wlpSuZd1gw5aXBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:17:55.786883Z"},"content_sha256":"9fa801fcba07aa600fb352cdd4d78e27166603a9f6e9809d45df52edc2554c0a","schema_version":"1.0","event_id":"sha256:9fa801fcba07aa600fb352cdd4d78e27166603a9f6e9809d45df52edc2554c0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AKF5Z5IPEYDRDS2MTERZNUZCLG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"F2A: An Innovative Approach for Prompt Injection by Utilizing Feign Security Detection Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Yupeng Ren","submitted_at":"2024-10-11T12:49:05Z","abstract_excerpt":"With the rapid development of Large Language Models (LLMs), numerous mature applications of LLMs have emerged in the field of content safety detection. However, we have found that LLMs exhibit blind trust in safety detection agents. The general LLMs can be compromised by hackers with this vulnerability. Hence, this paper proposed an attack named Feign Agent Attack (F2A).Through such malicious forgery methods, adding fake safety detection results into the prompt, the defense mechanism of LLMs can be bypassed, thereby obtaining harmful content and hijacking the normal conversation. Continually, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08776","kind":"arxiv","version":2},"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/2410.08776/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":"2026-07-05T09:20:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hnPe7KCgGtikQD/ZvFQLQI8CJYoUvpPyhv7TwqHHW2jJC+j0apnNprMD9YmeArQ4wqgrw1FRV+j8cAEIQjBvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:17:55.787396Z"},"content_sha256":"2c7064941abaf426d16f4ef44e45413dcc1d293841bede3243e5deeb1b700e37","schema_version":"1.0","event_id":"sha256:2c7064941abaf426d16f4ef44e45413dcc1d293841bede3243e5deeb1b700e37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AKF5Z5IPEYDRDS2MTERZNUZCLG/bundle.json","state_url":"https://pith.science/pith/AKF5Z5IPEYDRDS2MTERZNUZCLG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AKF5Z5IPEYDRDS2MTERZNUZCLG/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":"2026-08-08T02:17:55Z","links":{"resolver":"https://pith.science/pith/AKF5Z5IPEYDRDS2MTERZNUZCLG","bundle":"https://pith.science/pith/AKF5Z5IPEYDRDS2MTERZNUZCLG/bundle.json","state":"https://pith.science/pith/AKF5Z5IPEYDRDS2MTERZNUZCLG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AKF5Z5IPEYDRDS2MTERZNUZCLG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AKF5Z5IPEYDRDS2MTERZNUZCLG","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":"341b9d3ead9a6e6de7fc833f65de47bb669eff3324b3d5e0a63fec47320af988","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-10-11T12:49:05Z","title_canon_sha256":"5c350f87c62ee102bb673df9c6360879461da634c0515ad743e20b15b7cbf5de"},"schema_version":"1.0","source":{"id":"2410.08776","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08776","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08776v2","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08776","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_12","alias_value":"AKF5Z5IPEYDR","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_16","alias_value":"AKF5Z5IPEYDRDS2M","created_at":"2026-07-05T09:20:04Z"},{"alias_kind":"pith_short_8","alias_value":"AKF5Z5IP","created_at":"2026-07-05T09:20:04Z"}],"graph_snapshots":[{"event_id":"sha256:2c7064941abaf426d16f4ef44e45413dcc1d293841bede3243e5deeb1b700e37","target":"graph","created_at":"2026-07-05T09:20:04Z","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/2410.08776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid development of Large Language Models (LLMs), numerous mature applications of LLMs have emerged in the field of content safety detection. However, we have found that LLMs exhibit blind trust in safety detection agents. The general LLMs can be compromised by hackers with this vulnerability. Hence, this paper proposed an attack named Feign Agent Attack (F2A).Through such malicious forgery methods, adding fake safety detection results into the prompt, the defense mechanism of LLMs can be bypassed, thereby obtaining harmful content and hijacking the normal conversation. Continually, ","authors_text":"Yupeng Ren","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-10-11T12:49:05Z","title":"F2A: An Innovative Approach for Prompt Injection by Utilizing Feign Security Detection Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08776","kind":"arxiv","version":2},"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":"sha256:9fa801fcba07aa600fb352cdd4d78e27166603a9f6e9809d45df52edc2554c0a","target":"record","created_at":"2026-07-05T09:20:04Z","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":"341b9d3ead9a6e6de7fc833f65de47bb669eff3324b3d5e0a63fec47320af988","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-10-11T12:49:05Z","title_canon_sha256":"5c350f87c62ee102bb673df9c6360879461da634c0515ad743e20b15b7cbf5de"},"schema_version":"1.0","source":{"id":"2410.08776","kind":"arxiv","version":2}},"canonical_sha256":"028bdcf50f260711cb4c992396d3225981613ab57121896f59da0373f5001b14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"028bdcf50f260711cb4c992396d3225981613ab57121896f59da0373f5001b14","first_computed_at":"2026-07-05T09:20:04.929851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:04.929851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4EiEVM5I0WrhAD5obvXflfyas8N9rrca7MO2UkCFAQeF+22sAFAus1kox0rs/Ipywru5XYooLYN3NREV3OsiDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:04.930282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08776","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fa801fcba07aa600fb352cdd4d78e27166603a9f6e9809d45df52edc2554c0a","sha256:2c7064941abaf426d16f4ef44e45413dcc1d293841bede3243e5deeb1b700e37"],"state_sha256":"dda647d3830f7b7e3ca4d9ae706e5cbcc7975d9907b2e658174c6b129aa014be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"svqc8CMztUWPKpMnR3OYzMRt9+kuzPEpTXJyywc6+6M0JZxFwFVWIjqyAivjtiPksOZZDtrcocuprap/z1ovCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:17:55.792361Z","bundle_sha256":"e2bca1df7bf58bafb90079b10ea660af4b5e24decf7a97eb3f7722873cb0bfed"}}