{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VACSH4AHJ4B2VWEHEDYKBQEFFX","short_pith_number":"pith:VACSH4AH","canonical_record":{"source":{"id":"2308.10741","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-21T14:09:09Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"4082f21cc37b31a42aa72495ceea98d2fcb12afe985ea9b527e26a875aba73ea","abstract_canon_sha256":"492b1d430693d5e11f5c2ee264c0bfde496fb217d0ed5423b07c9123fa8344bb"},"schema_version":"1.0"},"canonical_sha256":"a80523f0074f03aad88720f0a0c0852df7a71465544140b6f349fcf249170f55","source":{"kind":"arxiv","id":"2308.10741","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10741","created_at":"2026-07-05T06:43:13Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10741v1","created_at":"2026-07-05T06:43:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10741","created_at":"2026-07-05T06:43:13Z"},{"alias_kind":"pith_short_12","alias_value":"VACSH4AHJ4B2","created_at":"2026-07-05T06:43:13Z"},{"alias_kind":"pith_short_16","alias_value":"VACSH4AHJ4B2VWEH","created_at":"2026-07-05T06:43:13Z"},{"alias_kind":"pith_short_8","alias_value":"VACSH4AH","created_at":"2026-07-05T06:43:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VACSH4AHJ4B2VWEHEDYKBQEFFX","target":"record","payload":{"canonical_record":{"source":{"id":"2308.10741","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-21T14:09:09Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"4082f21cc37b31a42aa72495ceea98d2fcb12afe985ea9b527e26a875aba73ea","abstract_canon_sha256":"492b1d430693d5e11f5c2ee264c0bfde496fb217d0ed5423b07c9123fa8344bb"},"schema_version":"1.0"},"canonical_sha256":"a80523f0074f03aad88720f0a0c0852df7a71465544140b6f349fcf249170f55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:13.815711Z","signature_b64":"p51MYSMNvkNP/5WIVAuYmSmmPzZ7amBjNTGkkdDRcsMFkO2YrKqgy9AKGPjLmwlxBgZemlXHpE/rc9iZ8QOQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a80523f0074f03aad88720f0a0c0852df7a71465544140b6f349fcf249170f55","last_reissued_at":"2026-07-05T06:43:13.815222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:13.815222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.10741","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:43:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HbZBsCnXBdz079slhfafvkfVQocB32z2MoC9IOytuMOS0tJ8YIMj2rBfkDZCPG3/331wlL7OZg9NG5NxSMefCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:02:53.581963Z"},"content_sha256":"c3604c384625ee5f0fde4230883c5eb50690c92c8bb695444ac9e93b042657b0","schema_version":"1.0","event_id":"sha256:c3604c384625ee5f0fde4230883c5eb50690c92c8bb695444ac9e93b042657b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VACSH4AHJ4B2VWEHEDYKBQEFFX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Adversarial Robustness of Multi-Modal Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Christian Schlarmann, Matthias Hein","submitted_at":"2023-08-21T14:09:09Z","abstract_excerpt":"Multi-modal foundation models combining vision and language models such as Flamingo or GPT-4 have recently gained enormous interest. Alignment of foundation models is used to prevent models from providing toxic or harmful output. While malicious users have successfully tried to jailbreak foundation models, an equally important question is if honest users could be harmed by malicious third-party content. In this paper we show that imperceivable attacks on images in order to change the caption output of a multi-modal foundation model can be used by malicious content providers to harm honest user"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10741","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2308.10741/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:43:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RU3gwMmviDgdk9PoEZezHlSW3rCNMj3GRvcCxoItN4QZaDWttKB0++CQxa5GAiylFeNHTiAK8wPXqewQqFEmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:02:53.582461Z"},"content_sha256":"eb91a6548a3fd4e7db9472f09a59d045928c6bef94c80833b7f6428ec3980a4a","schema_version":"1.0","event_id":"sha256:eb91a6548a3fd4e7db9472f09a59d045928c6bef94c80833b7f6428ec3980a4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VACSH4AHJ4B2VWEHEDYKBQEFFX/bundle.json","state_url":"https://pith.science/pith/VACSH4AHJ4B2VWEHEDYKBQEFFX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VACSH4AHJ4B2VWEHEDYKBQEFFX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T07:02:53Z","links":{"resolver":"https://pith.science/pith/VACSH4AHJ4B2VWEHEDYKBQEFFX","bundle":"https://pith.science/pith/VACSH4AHJ4B2VWEHEDYKBQEFFX/bundle.json","state":"https://pith.science/pith/VACSH4AHJ4B2VWEHEDYKBQEFFX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VACSH4AHJ4B2VWEHEDYKBQEFFX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VACSH4AHJ4B2VWEHEDYKBQEFFX","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":"492b1d430693d5e11f5c2ee264c0bfde496fb217d0ed5423b07c9123fa8344bb","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-21T14:09:09Z","title_canon_sha256":"4082f21cc37b31a42aa72495ceea98d2fcb12afe985ea9b527e26a875aba73ea"},"schema_version":"1.0","source":{"id":"2308.10741","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10741","created_at":"2026-07-05T06:43:13Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10741v1","created_at":"2026-07-05T06:43:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10741","created_at":"2026-07-05T06:43:13Z"},{"alias_kind":"pith_short_12","alias_value":"VACSH4AHJ4B2","created_at":"2026-07-05T06:43:13Z"},{"alias_kind":"pith_short_16","alias_value":"VACSH4AHJ4B2VWEH","created_at":"2026-07-05T06:43:13Z"},{"alias_kind":"pith_short_8","alias_value":"VACSH4AH","created_at":"2026-07-05T06:43:13Z"}],"graph_snapshots":[{"event_id":"sha256:eb91a6548a3fd4e7db9472f09a59d045928c6bef94c80833b7f6428ec3980a4a","target":"graph","created_at":"2026-07-05T06:43:13Z","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/2308.10741/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal foundation models combining vision and language models such as Flamingo or GPT-4 have recently gained enormous interest. Alignment of foundation models is used to prevent models from providing toxic or harmful output. While malicious users have successfully tried to jailbreak foundation models, an equally important question is if honest users could be harmed by malicious third-party content. In this paper we show that imperceivable attacks on images in order to change the caption output of a multi-modal foundation model can be used by malicious content providers to harm honest user","authors_text":"Christian Schlarmann, Matthias Hein","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-21T14:09:09Z","title":"On the Adversarial Robustness of Multi-Modal Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10741","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:c3604c384625ee5f0fde4230883c5eb50690c92c8bb695444ac9e93b042657b0","target":"record","created_at":"2026-07-05T06:43:13Z","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":"492b1d430693d5e11f5c2ee264c0bfde496fb217d0ed5423b07c9123fa8344bb","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-21T14:09:09Z","title_canon_sha256":"4082f21cc37b31a42aa72495ceea98d2fcb12afe985ea9b527e26a875aba73ea"},"schema_version":"1.0","source":{"id":"2308.10741","kind":"arxiv","version":1}},"canonical_sha256":"a80523f0074f03aad88720f0a0c0852df7a71465544140b6f349fcf249170f55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a80523f0074f03aad88720f0a0c0852df7a71465544140b6f349fcf249170f55","first_computed_at":"2026-07-05T06:43:13.815222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:13.815222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p51MYSMNvkNP/5WIVAuYmSmmPzZ7amBjNTGkkdDRcsMFkO2YrKqgy9AKGPjLmwlxBgZemlXHpE/rc9iZ8QOQCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:13.815711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.10741","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3604c384625ee5f0fde4230883c5eb50690c92c8bb695444ac9e93b042657b0","sha256:eb91a6548a3fd4e7db9472f09a59d045928c6bef94c80833b7f6428ec3980a4a"],"state_sha256":"264c44ca57916b798496f52a2d49e6522312646170af38f1c909e3a2e3418afb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"91/Zv8G6GmAQFnJXv4zfjSqN6lCjtmOfibNZCw4wKKSHm3fciTDjpZUijX07NG4z0Nqpe/Tyb78mLuf0fnuZDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:02:53.585758Z","bundle_sha256":"dc8eb34816cf3e521b7a0032f4d3df1bf90d8c4f3380f8483666c1fd755a7b12"}}