{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CDSFOEFSNLLVZCNYDH7A5LG7BH","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":"89681fde683d771ecb7b902de538854d5dfcd45adf8ab022f7a0d9a0fd08995f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-03-03T18:39:48Z","title_canon_sha256":"4afe742ffe126529a1658a779edcd3681ccdc9d70910268ea14d76804426d565"},"schema_version":"1.0","source":{"id":"2503.01811","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01811","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01811v1","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01811","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"pith_short_12","alias_value":"CDSFOEFSNLLV","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"pith_short_16","alias_value":"CDSFOEFSNLLVZCNY","created_at":"2026-07-05T10:23:16Z"},{"alias_kind":"pith_short_8","alias_value":"CDSFOEFS","created_at":"2026-07-05T10:23:16Z"}],"graph_snapshots":[{"event_id":"sha256:62851829e8bd7c6d0f6983e25d97f31e7cbdecd5a1ba1475530632c74c6cec69","target":"graph","created_at":"2026-07-05T10:23:16Z","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/2503.01811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce AutoAdvExBench, a benchmark to evaluate if large language models (LLMs) can autonomously exploit defenses to adversarial examples. Unlike existing security benchmarks that often serve as proxies for real-world tasks, bench directly measures LLMs' success on tasks regularly performed by machine learning security experts. This approach offers a significant advantage: if a LLM could solve the challenges presented in bench, it would immediately present practical utility for adversarial machine learning researchers. We then design a strong agent that is capable of breaking 75% of CTF-l","authors_text":"Edoardo Debenedetti, Florian Tram\\`er, Javier Rando, Milad Nasr, Nicholas Carlini","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-03-03T18:39:48Z","title":"AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01811","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":"sha256:75db221c6633e3ea4f4038f1241cdccf5f37a10c08ed41a4ddbc455e9245bdf8","target":"record","created_at":"2026-07-05T10:23:16Z","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":"89681fde683d771ecb7b902de538854d5dfcd45adf8ab022f7a0d9a0fd08995f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-03-03T18:39:48Z","title_canon_sha256":"4afe742ffe126529a1658a779edcd3681ccdc9d70910268ea14d76804426d565"},"schema_version":"1.0","source":{"id":"2503.01811","kind":"arxiv","version":1}},"canonical_sha256":"10e45710b26ad75c89b819fe0eacdf09ec9e751f6b6d881e2956422ff0f0269f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10e45710b26ad75c89b819fe0eacdf09ec9e751f6b6d881e2956422ff0f0269f","first_computed_at":"2026-07-05T10:23:16.001170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:16.001170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NU0gLr1O1qLbFR017t+fz1vK9s1PDNtb2MhFDr0s71UnY7umm4n07TIqAkweCAWymDIjGliWm18PIdTK20MWDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:16.001748Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01811","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75db221c6633e3ea4f4038f1241cdccf5f37a10c08ed41a4ddbc455e9245bdf8","sha256:62851829e8bd7c6d0f6983e25d97f31e7cbdecd5a1ba1475530632c74c6cec69"],"state_sha256":"ebc3c26055099456d4a77b4def6707b26d21f06ef575939d20d7bf1ae560354b"}