{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U3JGL4NBZDQMQ33IJZRIZFYRIY","short_pith_number":"pith:U3JGL4NB","canonical_record":{"source":{"id":"2409.15398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-09-23T10:18:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"729b3e109e717f7df4c864eda90913eb82632a2f5969b6cec60719f6ec185ff6","abstract_canon_sha256":"40965bc9fda922a721a3e73b8703cb6c2e81bf419b8974d46a4beee228541141"},"schema_version":"1.0"},"canonical_sha256":"a6d265f1a1c8e0c86f684e628c97114608efa941d2b4fdb4c4bb2712525a7fe8","source":{"kind":"arxiv","id":"2409.15398","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15398","created_at":"2026-07-05T09:10:54Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15398v1","created_at":"2026-07-05T09:10:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15398","created_at":"2026-07-05T09:10:54Z"},{"alias_kind":"pith_short_12","alias_value":"U3JGL4NBZDQM","created_at":"2026-07-05T09:10:54Z"},{"alias_kind":"pith_short_16","alias_value":"U3JGL4NBZDQMQ33I","created_at":"2026-07-05T09:10:54Z"},{"alias_kind":"pith_short_8","alias_value":"U3JGL4NB","created_at":"2026-07-05T09:10:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U3JGL4NBZDQMQ33IJZRIZFYRIY","target":"record","payload":{"canonical_record":{"source":{"id":"2409.15398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-09-23T10:18:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"729b3e109e717f7df4c864eda90913eb82632a2f5969b6cec60719f6ec185ff6","abstract_canon_sha256":"40965bc9fda922a721a3e73b8703cb6c2e81bf419b8974d46a4beee228541141"},"schema_version":"1.0"},"canonical_sha256":"a6d265f1a1c8e0c86f684e628c97114608efa941d2b4fdb4c4bb2712525a7fe8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:54.442264Z","signature_b64":"C1jefifhTDrKMu+d5SI+Jbw+Qv3s0WhzI0m0Ma2WOYWsnqWqv1xXWNrwiBHC9MpLXj19F0Dc1cYPS1I9xoETDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6d265f1a1c8e0c86f684e628c97114608efa941d2b4fdb4c4bb2712525a7fe8","last_reissued_at":"2026-07-05T09:10:54.441779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:54.441779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.15398","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":"2026-07-05T09:10:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M/sij43dwU4M1TQmoNa2lLfSVG9nAJKKpB6Y/QQMQKIpPa+gf0FWQ+Q3QOUWc4HRZA+SsCaRGairzlJ+dkd5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:03:27.188819Z"},"content_sha256":"c374e93cb1a75dcda3d251e14a21fbd6cb8f2a6f0f68dae55039775583d06f18","schema_version":"1.0","event_id":"sha256:c374e93cb1a75dcda3d251e14a21fbd6cb8f2a6f0f68dae55039775583d06f18"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U3JGL4NBZDQMQ33IJZRIZFYRIY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Ambrish Rawat, Beat Buesser, Elizabeth M. Daly, Erik Miehling, Giandomenico Cornacchia, Giulio Zizzo, Kieran Fraser, Kush R. Varshney, Mark Purcell, Muhammad Zaid Hameed, Pin-Yu Chen, Prasanna Sattigeri, Stefan Schoepf","submitted_at":"2024-09-23T10:18:10Z","abstract_excerpt":"As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and multi-modal systems. Red-teaming has gained importance in proactively identifying weaknesses in these systems, while blue-teaming works to protect against such adversarial attacks. Despite growing academic interest in adversarial risks for generative AI, there is limited guidance tailored for practitioners to assess and mitigate these challenges in real-world enviro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15398","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/2409.15398/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":"2026-07-05T09:10:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B6p/ZjbsklfFFeTuqIYzFxjmJ8Y4JVffBlwguYMljtGreDuB9IrdlC7uEktywGSZQQMWBwVfBbAhKjTGwg7RAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:03:27.189354Z"},"content_sha256":"4512f239e05404ec5115490b75223992a65e9ac9e7384ec81f3bef556bc5b0e7","schema_version":"1.0","event_id":"sha256:4512f239e05404ec5115490b75223992a65e9ac9e7384ec81f3bef556bc5b0e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U3JGL4NBZDQMQ33IJZRIZFYRIY/bundle.json","state_url":"https://pith.science/pith/U3JGL4NBZDQMQ33IJZRIZFYRIY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U3JGL4NBZDQMQ33IJZRIZFYRIY/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":"2026-08-06T10:03:27Z","links":{"resolver":"https://pith.science/pith/U3JGL4NBZDQMQ33IJZRIZFYRIY","bundle":"https://pith.science/pith/U3JGL4NBZDQMQ33IJZRIZFYRIY/bundle.json","state":"https://pith.science/pith/U3JGL4NBZDQMQ33IJZRIZFYRIY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U3JGL4NBZDQMQ33IJZRIZFYRIY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U3JGL4NBZDQMQ33IJZRIZFYRIY","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":"40965bc9fda922a721a3e73b8703cb6c2e81bf419b8974d46a4beee228541141","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-09-23T10:18:10Z","title_canon_sha256":"729b3e109e717f7df4c864eda90913eb82632a2f5969b6cec60719f6ec185ff6"},"schema_version":"1.0","source":{"id":"2409.15398","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15398","created_at":"2026-07-05T09:10:54Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15398v1","created_at":"2026-07-05T09:10:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15398","created_at":"2026-07-05T09:10:54Z"},{"alias_kind":"pith_short_12","alias_value":"U3JGL4NBZDQM","created_at":"2026-07-05T09:10:54Z"},{"alias_kind":"pith_short_16","alias_value":"U3JGL4NBZDQMQ33I","created_at":"2026-07-05T09:10:54Z"},{"alias_kind":"pith_short_8","alias_value":"U3JGL4NB","created_at":"2026-07-05T09:10:54Z"}],"graph_snapshots":[{"event_id":"sha256:4512f239e05404ec5115490b75223992a65e9ac9e7384ec81f3bef556bc5b0e7","target":"graph","created_at":"2026-07-05T09:10:54Z","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/2409.15398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and multi-modal systems. Red-teaming has gained importance in proactively identifying weaknesses in these systems, while blue-teaming works to protect against such adversarial attacks. Despite growing academic interest in adversarial risks for generative AI, there is limited guidance tailored for practitioners to assess and mitigate these challenges in real-world enviro","authors_text":"Ambrish Rawat, Beat Buesser, Elizabeth M. Daly, Erik Miehling, Giandomenico Cornacchia, Giulio Zizzo, Kieran Fraser, Kush R. Varshney, Mark Purcell, Muhammad Zaid Hameed, Pin-Yu Chen, Prasanna Sattigeri, Stefan Schoepf","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-09-23T10:18:10Z","title":"Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15398","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:c374e93cb1a75dcda3d251e14a21fbd6cb8f2a6f0f68dae55039775583d06f18","target":"record","created_at":"2026-07-05T09:10:54Z","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":"40965bc9fda922a721a3e73b8703cb6c2e81bf419b8974d46a4beee228541141","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-09-23T10:18:10Z","title_canon_sha256":"729b3e109e717f7df4c864eda90913eb82632a2f5969b6cec60719f6ec185ff6"},"schema_version":"1.0","source":{"id":"2409.15398","kind":"arxiv","version":1}},"canonical_sha256":"a6d265f1a1c8e0c86f684e628c97114608efa941d2b4fdb4c4bb2712525a7fe8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6d265f1a1c8e0c86f684e628c97114608efa941d2b4fdb4c4bb2712525a7fe8","first_computed_at":"2026-07-05T09:10:54.441779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:10:54.441779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C1jefifhTDrKMu+d5SI+Jbw+Qv3s0WhzI0m0Ma2WOYWsnqWqv1xXWNrwiBHC9MpLXj19F0Dc1cYPS1I9xoETDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:10:54.442264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.15398","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c374e93cb1a75dcda3d251e14a21fbd6cb8f2a6f0f68dae55039775583d06f18","sha256:4512f239e05404ec5115490b75223992a65e9ac9e7384ec81f3bef556bc5b0e7"],"state_sha256":"299b226e49f1a33ced5d7e6cd1c4b8400dbb541a783cd2ad0b6c36c0de4eada2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aoL2SOmffz1EMeGbUtwaceo9Cn62z8RkXR3Zo1u42SB6eTvOK26g9KseYrnhivUTyYq6h+YdBLQ5EKgs8/klBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T10:03:27.192731Z","bundle_sha256":"f10822ac61df3b98b71f6e778ae37b3cbe53e677417caa0cccf99bf87f56f9ec"}}