{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:27YTNLKHTOSO25ANWICGUTFZMK","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":"29cf598ef1606b2ad6ea1278a0734218fbb7cc7c83be7bdb93465a699afbdd2b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T05:40:54Z","title_canon_sha256":"4a59aafb1f4c3ecd92d3a7270c4f7af4707088d7d402ca45f730a5cde437022f"},"schema_version":"1.0","source":{"id":"2410.13236","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.13236","created_at":"2026-07-05T09:21:57Z"},{"alias_kind":"arxiv_version","alias_value":"2410.13236v1","created_at":"2026-07-05T09:21:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13236","created_at":"2026-07-05T09:21:57Z"},{"alias_kind":"pith_short_12","alias_value":"27YTNLKHTOSO","created_at":"2026-07-05T09:21:57Z"},{"alias_kind":"pith_short_16","alias_value":"27YTNLKHTOSO25AN","created_at":"2026-07-05T09:21:57Z"},{"alias_kind":"pith_short_8","alias_value":"27YTNLKH","created_at":"2026-07-05T09:21:57Z"}],"graph_snapshots":[{"event_id":"sha256:2f6834eb3f44e44a8b9b2ef2d7bfb879ae9907d1be06d7ee7aa13dac6bad3b40","target":"graph","created_at":"2026-07-05T09:21:57Z","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/2410.13236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbreak attacks have been proposed to bypass the safety alignment and cause the model to produce harmful responses. We introduce Self-supervised Prompt INjection (SPIN) which can detect and reverse these various attacks on LLMs. As our self-supervised prompt defense is done at inference-time, it is also compatible with existing alignment and adds an additional layer of safety for defense. Our benchmarks demonstrate that ","authors_text":"Chengzhi Mao, Junfeng Yang, Leon Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T05:40:54Z","title":"SPIN: Self-Supervised Prompt INjection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13236","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:b9e39fc92d12e27a4712d59311b2cee69bd2e527617d90d8066868fc239a815d","target":"record","created_at":"2026-07-05T09:21:57Z","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":"29cf598ef1606b2ad6ea1278a0734218fbb7cc7c83be7bdb93465a699afbdd2b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T05:40:54Z","title_canon_sha256":"4a59aafb1f4c3ecd92d3a7270c4f7af4707088d7d402ca45f730a5cde437022f"},"schema_version":"1.0","source":{"id":"2410.13236","kind":"arxiv","version":1}},"canonical_sha256":"d7f136ad479ba4ed740db2046a4cb962990950896b2204faea838321951e50fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7f136ad479ba4ed740db2046a4cb962990950896b2204faea838321951e50fb","first_computed_at":"2026-07-05T09:21:57.513338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:57.513338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VrwE8HESYzVUjiSISDMH0me1a2sAcUIoLHO93UqqmAgM7Sw6FdIR5rGkFroQP9UQ+P4Lbdk4HPrMJdmsrC+oDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:57.513888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.13236","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9e39fc92d12e27a4712d59311b2cee69bd2e527617d90d8066868fc239a815d","sha256:2f6834eb3f44e44a8b9b2ef2d7bfb879ae9907d1be06d7ee7aa13dac6bad3b40"],"state_sha256":"b3ce3c424b8c37e059bc4ac5ed71f1f4cbda046fd9c2c84e014bd5deb4b5eda7"}