{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q6TUQA2AIJLE2IDHIO3MI6QHLO","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":"61a9691a79d172271b39ad2ad6db02720fad7f65fe526405daf662d372d52c87","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-11T22:07:47Z","title_canon_sha256":"861a42a517fe43e5dac7009f0ec42bb3e8e419aa7414963e483f0d64a49e0b9f"},"schema_version":"1.0","source":{"id":"2502.07987","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07987","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07987v3","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07987","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"pith_short_12","alias_value":"Q6TUQA2AIJLE","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"pith_short_16","alias_value":"Q6TUQA2AIJLE2IDH","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"pith_short_8","alias_value":"Q6TUQA2A","created_at":"2026-07-05T11:16:06Z"}],"graph_snapshots":[{"event_id":"sha256:275cc0515ab8a051cfa5c18efa342895c5a33fcc58cacaa130a4a070206ace7c","target":"graph","created_at":"2026-07-05T11:16:06Z","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/2502.07987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a universal adversarial attack on multimodal Large Language Models (LLMs) that leverages a single optimized image to override alignment safeguards across diverse queries and even multiple models. By backpropagating through the vision encoder and language head, we craft a synthetic image that forces the model to respond with a targeted phrase (e.g., \"Sure, here it is\") or otherwise unsafe content -- even for harmful prompts. In experiments on the SafeBench and MM-SafetyBench benchmarks, our method achieves higher attack success rates than existing baselines, including text-only unive","authors_text":"Andrey Kuznetsov, Anton Razzhigaev, Matvey Mikhalchuk, Nikita Kurdiukov, Polina Druzhinina, Temurbek Rahmatullaev","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-11T22:07:47Z","title":"Universal Adversarial Attack on Aligned Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07987","kind":"arxiv","version":3},"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:d8a2c9d80fd03b615895cb2254d2e97dbd43dcedfe5f5f81ce7a387f38fa622e","target":"record","created_at":"2026-07-05T11:16:06Z","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":"61a9691a79d172271b39ad2ad6db02720fad7f65fe526405daf662d372d52c87","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-11T22:07:47Z","title_canon_sha256":"861a42a517fe43e5dac7009f0ec42bb3e8e419aa7414963e483f0d64a49e0b9f"},"schema_version":"1.0","source":{"id":"2502.07987","kind":"arxiv","version":3}},"canonical_sha256":"87a748034042564d206743b6c47a075b97ae7ed330f23b45e418c4b3d1d99da1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87a748034042564d206743b6c47a075b97ae7ed330f23b45e418c4b3d1d99da1","first_computed_at":"2026-07-05T11:16:06.088839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:06.088839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DSX6hmPBVdWzhMn3QqLsGtnyYt43nhJRQr+2fIfjtKGLlRH5Y3p5jhFomJQYHarKSWQ0NxmwnOtz7sovOeQ1BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:06.089356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07987","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8a2c9d80fd03b615895cb2254d2e97dbd43dcedfe5f5f81ce7a387f38fa622e","sha256:275cc0515ab8a051cfa5c18efa342895c5a33fcc58cacaa130a4a070206ace7c"],"state_sha256":"953006339acb0b092b4e5b9c4b02421f9016a71ac0a7a0b845ae3c8f871f8c6e"}