{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NXI6KLT66EEUM3RVSNJQRSN5PJ","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":"6a0b412d8e869730fb1bd40839a90b94c5b434b6e8b774f14ca962f13fad2700","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-07-12T07:18:05Z","title_canon_sha256":"a2886c8b8d8d904e9a121d15200b511138694a8486d372dc170ac5e859529e2c"},"schema_version":"1.0","source":{"id":"2407.09050","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09050","created_at":"2026-07-05T09:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09050v2","created_at":"2026-07-05T09:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09050","created_at":"2026-07-05T09:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"NXI6KLT66EEU","created_at":"2026-07-05T09:03:54Z"},{"alias_kind":"pith_short_16","alias_value":"NXI6KLT66EEUM3RV","created_at":"2026-07-05T09:03:54Z"},{"alias_kind":"pith_short_8","alias_value":"NXI6KLT6","created_at":"2026-07-05T09:03:54Z"}],"graph_snapshots":[{"event_id":"sha256:1bba5fa7153fb4cfdeadfd58db5d4020062634c5a5a5e42fa5963a539bf3637f","target":"graph","created_at":"2026-07-05T09:03:54Z","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/2407.09050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have become the cornerstone of today's generative AI ecosystem, sparking intense competition among tech giants and startups. In particular, an MLLM generates a text response given a prompt consisting of an image and a question. While state-of-the-art MLLMs use safety filters and alignment techniques to refuse unsafe prompts, in this work, we introduce MLLM-Refusal, the first method that induces refusals for safe prompts. In particular, our MLLM-Refusal optimizes a nearly-imperceptible refusal perturbation and adds it to an image, causing target MLLMs to","authors_text":"Hongbin Liu, Neil Zhenqiang Gong, Yuepeng Hu, Zedian Shao","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-07-12T07:18:05Z","title":"Refusing Safe Prompts for Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09050","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:cf3398dbd46e8e9c182bd6db7d3a352f15ccdbdb6108330711ea950fa21ad7ca","target":"record","created_at":"2026-07-05T09:03:54Z","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":"6a0b412d8e869730fb1bd40839a90b94c5b434b6e8b774f14ca962f13fad2700","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-07-12T07:18:05Z","title_canon_sha256":"a2886c8b8d8d904e9a121d15200b511138694a8486d372dc170ac5e859529e2c"},"schema_version":"1.0","source":{"id":"2407.09050","kind":"arxiv","version":2}},"canonical_sha256":"6dd1e52e7ef109466e35935308c9bd7a55351ff59dffaf6cec92f3840d36b37c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dd1e52e7ef109466e35935308c9bd7a55351ff59dffaf6cec92f3840d36b37c","first_computed_at":"2026-07-05T09:03:54.546099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:54.546099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2M7wRT3fRgncq/x9gKXeAvsCnVdubkbcjX+9s9smVSnD0GvAbhr6S1qdt9xCi3Jt7HR7OeTGCJvRA6T98qS2CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:54.546547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.09050","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf3398dbd46e8e9c182bd6db7d3a352f15ccdbdb6108330711ea950fa21ad7ca","sha256:1bba5fa7153fb4cfdeadfd58db5d4020062634c5a5a5e42fa5963a539bf3637f"],"state_sha256":"05895b6d530468203dd223d462cb2bc353581e926b536a41c56e555b09130cbe"}