{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2BDSBAY62MO7F2J43P6BHTGHZB","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":"a02b94de8fd6d72e64de62dda2a17196c568a12370030d8887c4f007c1c56db5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T17:36:05Z","title_canon_sha256":"7fb7141be7565157956cdc974687c028326345c99f3250b947ccae3b246624c0"},"schema_version":"1.0","source":{"id":"2504.20965","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20965","created_at":"2026-07-05T11:21:45Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20965v2","created_at":"2026-07-05T11:21:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20965","created_at":"2026-07-05T11:21:45Z"},{"alias_kind":"pith_short_12","alias_value":"2BDSBAY62MO7","created_at":"2026-07-05T11:21:45Z"},{"alias_kind":"pith_short_16","alias_value":"2BDSBAY62MO7F2J4","created_at":"2026-07-05T11:21:45Z"},{"alias_kind":"pith_short_8","alias_value":"2BDSBAY6","created_at":"2026-07-05T11:21:45Z"}],"graph_snapshots":[{"event_id":"sha256:390342f025be684128153ce6f71a957ff4a4296a1f1eaacc9e5de1425055445a","target":"graph","created_at":"2026-07-05T11:21:45Z","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/2504.20965/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce AegisLLM, a cooperative multi-agent defense against adversarial attacks and information leakage. In AegisLLM, a structured workflow of autonomous agents - orchestrator, deflector, responder, and evaluator - collaborate to ensure safe and compliant LLM outputs, while self-improving over time through prompt optimization. We show that scaling agentic reasoning system at test-time - both by incorporating additional agent roles and by leveraging automated prompt optimization (such as DSPy)- substantially enhances robustness without compromising model utility. This test-time defense ena","authors_text":"Bang An, Bhavya Kailkhura, Brian R. Bartoldson, Furong Huang, Shayan Shabihi, Tom Goldstein, Zikui Cai, Zora Che","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T17:36:05Z","title":"AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20965","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:fe1b1ccddc8a83b80974bae6c1f9d9863a63e1928fe3326375e8e172aaf68396","target":"record","created_at":"2026-07-05T11:21:45Z","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":"a02b94de8fd6d72e64de62dda2a17196c568a12370030d8887c4f007c1c56db5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T17:36:05Z","title_canon_sha256":"7fb7141be7565157956cdc974687c028326345c99f3250b947ccae3b246624c0"},"schema_version":"1.0","source":{"id":"2504.20965","kind":"arxiv","version":2}},"canonical_sha256":"d04720831ed31df2e93cdbfc13ccc7c84e85be0a376b04f78e28d8f42da52d0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d04720831ed31df2e93cdbfc13ccc7c84e85be0a376b04f78e28d8f42da52d0f","first_computed_at":"2026-07-05T11:21:45.891502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:45.891502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2KLBXHyzuCusBz7huRjx2Ap50bxN9PekjyH7FtB/qE5OCUjXqvNFz21zRSTtHEdQDroKgJ4rSS0GAqbhr5rBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:45.892070Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20965","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe1b1ccddc8a83b80974bae6c1f9d9863a63e1928fe3326375e8e172aaf68396","sha256:390342f025be684128153ce6f71a957ff4a4296a1f1eaacc9e5de1425055445a"],"state_sha256":"29fffab95abb42f0ec939cd2fbb7a0786b9c5e6403dca92137ab7ad21c64e3dd"}