{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BXNI3C5MHM23GFOSBFQAYAHBUF","short_pith_number":"pith:BXNI3C5M","canonical_record":{"source":{"id":"2507.05093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-07T15:13:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd572b1aa9b55dcd21b3046e6e404a9e06598b509b30372c0a0b956916081552","abstract_canon_sha256":"cf93ea8d4aa6c7b9aa8530d7cb50853c719d5b284d5ce8cb05fecdcf8d1a6ce5"},"schema_version":"1.0"},"canonical_sha256":"0dda8d8bac3b35b315d209600c00e1a17df265cf588ca23a93aa6ca76ee62525","source":{"kind":"arxiv","id":"2507.05093","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05093","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05093v1","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05093","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_12","alias_value":"BXNI3C5MHM23","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_16","alias_value":"BXNI3C5MHM23GFOS","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_8","alias_value":"BXNI3C5M","created_at":"2026-07-05T11:33:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BXNI3C5MHM23GFOSBFQAYAHBUF","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-07T15:13:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fd572b1aa9b55dcd21b3046e6e404a9e06598b509b30372c0a0b956916081552","abstract_canon_sha256":"cf93ea8d4aa6c7b9aa8530d7cb50853c719d5b284d5ce8cb05fecdcf8d1a6ce5"},"schema_version":"1.0"},"canonical_sha256":"0dda8d8bac3b35b315d209600c00e1a17df265cf588ca23a93aa6ca76ee62525","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:08.940048Z","signature_b64":"Htcp7tHT2fiBeibVJRq8aQ+bpdYK6X8Wc1/gC7sQbFljNSx5m7Ob/v9BV/ZeW3j72bu9FU5LQvdUd1HHAd57AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dda8d8bac3b35b315d209600c00e1a17df265cf588ca23a93aa6ca76ee62525","last_reissued_at":"2026-07-05T11:33:08.939639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:08.939639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05093","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":"2026-07-05T11:33:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IW0gQkgIDH23TPwKC9vXssVg6swbQ2sJpJvrGRbCELIxvEsEw0cdPDYixAs1km7YqWh+M1J1W1vQY6oYGvl5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:00:32.933891Z"},"content_sha256":"0fdb90e0ace7c0c40359a33475fe3c4a25cf8a211b9ccb567273b4e45eab0f19","schema_version":"1.0","event_id":"sha256:0fdb90e0ace7c0c40359a33475fe3c4a25cf8a211b9ccb567273b4e45eab0f19"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BXNI3C5MHM23GFOSBFQAYAHBUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Hidden Threat in Plain Text: Attacking RAG Data Loaders","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Alberto Castagnaro, Luca Pajola, Mauro Conti, Simeone Pizzi, Umberto Salviati","submitted_at":"2025-07-07T15:13:54Z","abstract_excerpt":"Large Language Models (LLMs) have transformed human-machine interaction since ChatGPT's 2022 debut, with Retrieval-Augmented Generation (RAG) emerging as a key framework that enhances LLM outputs by integrating external knowledge. However, RAG's reliance on ingesting external documents introduces new vulnerabilities. This paper exposes a critical security gap at the data loading stage, where malicious actors can stealthily corrupt RAG pipelines by exploiting document ingestion.\n  We propose a taxonomy of 9 knowledge-based poisoning attacks and introduce two novel threat vectors -- Content Obfu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05093","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/2507.05093/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":"2026-07-05T11:33:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dRLbUqsZR/EbNvYjpd2qysPEZXRB5KTZKdN+s7HCuhWNgkdOfo8flAe7IHMFgUH7EiBtDNRYxcMO9nZuOsXYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:00:32.934724Z"},"content_sha256":"acfa8dfb5f15a78abd76ab7bed2b416c29255d075e09063ffa08af142d13b0d1","schema_version":"1.0","event_id":"sha256:acfa8dfb5f15a78abd76ab7bed2b416c29255d075e09063ffa08af142d13b0d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BXNI3C5MHM23GFOSBFQAYAHBUF/bundle.json","state_url":"https://pith.science/pith/BXNI3C5MHM23GFOSBFQAYAHBUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BXNI3C5MHM23GFOSBFQAYAHBUF/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":"2026-08-07T18:00:32Z","links":{"resolver":"https://pith.science/pith/BXNI3C5MHM23GFOSBFQAYAHBUF","bundle":"https://pith.science/pith/BXNI3C5MHM23GFOSBFQAYAHBUF/bundle.json","state":"https://pith.science/pith/BXNI3C5MHM23GFOSBFQAYAHBUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BXNI3C5MHM23GFOSBFQAYAHBUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BXNI3C5MHM23GFOSBFQAYAHBUF","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":"cf93ea8d4aa6c7b9aa8530d7cb50853c719d5b284d5ce8cb05fecdcf8d1a6ce5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-07T15:13:54Z","title_canon_sha256":"fd572b1aa9b55dcd21b3046e6e404a9e06598b509b30372c0a0b956916081552"},"schema_version":"1.0","source":{"id":"2507.05093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05093","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05093v1","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05093","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_12","alias_value":"BXNI3C5MHM23","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_16","alias_value":"BXNI3C5MHM23GFOS","created_at":"2026-07-05T11:33:08Z"},{"alias_kind":"pith_short_8","alias_value":"BXNI3C5M","created_at":"2026-07-05T11:33:08Z"}],"graph_snapshots":[{"event_id":"sha256:acfa8dfb5f15a78abd76ab7bed2b416c29255d075e09063ffa08af142d13b0d1","target":"graph","created_at":"2026-07-05T11:33:08Z","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/2507.05093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have transformed human-machine interaction since ChatGPT's 2022 debut, with Retrieval-Augmented Generation (RAG) emerging as a key framework that enhances LLM outputs by integrating external knowledge. However, RAG's reliance on ingesting external documents introduces new vulnerabilities. This paper exposes a critical security gap at the data loading stage, where malicious actors can stealthily corrupt RAG pipelines by exploiting document ingestion.\n  We propose a taxonomy of 9 knowledge-based poisoning attacks and introduce two novel threat vectors -- Content Obfu","authors_text":"Alberto Castagnaro, Luca Pajola, Mauro Conti, Simeone Pizzi, Umberto Salviati","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-07T15:13:54Z","title":"The Hidden Threat in Plain Text: Attacking RAG Data Loaders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05093","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":"sha256:0fdb90e0ace7c0c40359a33475fe3c4a25cf8a211b9ccb567273b4e45eab0f19","target":"record","created_at":"2026-07-05T11:33:08Z","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":"cf93ea8d4aa6c7b9aa8530d7cb50853c719d5b284d5ce8cb05fecdcf8d1a6ce5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-07T15:13:54Z","title_canon_sha256":"fd572b1aa9b55dcd21b3046e6e404a9e06598b509b30372c0a0b956916081552"},"schema_version":"1.0","source":{"id":"2507.05093","kind":"arxiv","version":1}},"canonical_sha256":"0dda8d8bac3b35b315d209600c00e1a17df265cf588ca23a93aa6ca76ee62525","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dda8d8bac3b35b315d209600c00e1a17df265cf588ca23a93aa6ca76ee62525","first_computed_at":"2026-07-05T11:33:08.939639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:08.939639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Htcp7tHT2fiBeibVJRq8aQ+bpdYK6X8Wc1/gC7sQbFljNSx5m7Ob/v9BV/ZeW3j72bu9FU5LQvdUd1HHAd57AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:08.940048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fdb90e0ace7c0c40359a33475fe3c4a25cf8a211b9ccb567273b4e45eab0f19","sha256:acfa8dfb5f15a78abd76ab7bed2b416c29255d075e09063ffa08af142d13b0d1"],"state_sha256":"4cd57165df3f590f5bbd873e82a8de901fc75ec80c96e3c8949efa4e14c479a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fPD/Cw7zmBGaAdzeiqQ5iR2grQRse2F7TbmzKEhbBkqQDHlLCCn02PEjupb4cnMDNvHwbOin17+AXYMloz8IAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:00:32.941108Z","bundle_sha256":"16af07c5ead4d0e746e9189f96378eb7455ae9b65d3d15974b19ea93477f28ee"}}