{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MMWMOW6RM4LEENXVKMZ2POKDL6","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":"17779300e0bd682c1507295e5e2bffec540ccf575c0edce152635444fc045fbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-13T03:35:43Z","title_canon_sha256":"6a086fae6c28898b21bf8b5aa0a761969da3964a4a2f08d3cd89ceba14315afa"},"schema_version":"1.0","source":{"id":"2312.07876","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07876","created_at":"2026-07-05T07:23:38Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07876v1","created_at":"2026-07-05T07:23:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07876","created_at":"2026-07-05T07:23:38Z"},{"alias_kind":"pith_short_12","alias_value":"MMWMOW6RM4LE","created_at":"2026-07-05T07:23:38Z"},{"alias_kind":"pith_short_16","alias_value":"MMWMOW6RM4LEENXV","created_at":"2026-07-05T07:23:38Z"},{"alias_kind":"pith_short_8","alias_value":"MMWMOW6R","created_at":"2026-07-05T07:23:38Z"}],"graph_snapshots":[{"event_id":"sha256:85e0096c878147c8ce3ac02ba809dce2c69ead03e81d2e0e08a29f53457d081d","target":"graph","created_at":"2026-07-05T07:23:38Z","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/2312.07876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) such as GPT and Llama2 are increasingly adopted in many safety-critical applications. Their security is thus essential. Even with considerable efforts spent on reinforcement learning from human feedback (RLHF), recent studies have shown that LLMs are still subject to attacks such as adversarial perturbation and Trojan attacks. Further research is thus needed to evaluate their security and/or understand the lack of it. In this work, we propose a framework for conducting light-weight causality-analysis of LLMs at the token, layer, and neuron level. We applied our fra","authors_text":"Jun Sun, Wei Zhao, Zhe Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-13T03:35:43Z","title":"Causality Analysis for Evaluating the Security of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07876","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:c7dfc6742447340bccea2dfbc84cea705592da37db3688fdfe1f509cf17cc680","target":"record","created_at":"2026-07-05T07:23:38Z","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":"17779300e0bd682c1507295e5e2bffec540ccf575c0edce152635444fc045fbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-12-13T03:35:43Z","title_canon_sha256":"6a086fae6c28898b21bf8b5aa0a761969da3964a4a2f08d3cd89ceba14315afa"},"schema_version":"1.0","source":{"id":"2312.07876","kind":"arxiv","version":1}},"canonical_sha256":"632cc75bd167164236f55333a7b9435fb85897d2e5d0ee0593c0dcf56f9b1df1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"632cc75bd167164236f55333a7b9435fb85897d2e5d0ee0593c0dcf56f9b1df1","first_computed_at":"2026-07-05T07:23:38.658388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:38.658388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6N2+JSUAosNvXFhkZ0XGx10xL7uBa0Ru8TJcxcS9PlnmaK7TbodFuBp7aeLlqI9kJZmqfV2hAmaY3XrekZUgBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:38.658859Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.07876","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7dfc6742447340bccea2dfbc84cea705592da37db3688fdfe1f509cf17cc680","sha256:85e0096c878147c8ce3ac02ba809dce2c69ead03e81d2e0e08a29f53457d081d"],"state_sha256":"108cea55179deff4146269e54d05eb6808b4bed47b919ecc5fe412c930bd67c0"}