{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YAPS373RSXNGCFULBW6BA6QYWU","short_pith_number":"pith:YAPS373R","canonical_record":{"source":{"id":"2404.19287","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T06:34:21Z","cross_cats_sorted":[],"title_canon_sha256":"7c893851de00fc9fb2007be823d52d8e683a07e310f666d6ebd209473dbab47c","abstract_canon_sha256":"cdc131bf332d2eb4aaa1e113f2e62441e3b448dbdb7e6875073408c20b4129ae"},"schema_version":"1.0"},"canonical_sha256":"c01f2dff7195da61168b0dbc107a18b53106812df7242f98efbe9ffab4a27082","source":{"kind":"arxiv","id":"2404.19287","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.19287","created_at":"2026-07-05T09:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"2404.19287v3","created_at":"2026-07-05T09:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19287","created_at":"2026-07-05T09:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"YAPS373RSXNG","created_at":"2026-07-05T09:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"YAPS373RSXNGCFUL","created_at":"2026-07-05T09:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"YAPS373R","created_at":"2026-07-05T09:34:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YAPS373RSXNGCFULBW6BA6QYWU","target":"record","payload":{"canonical_record":{"source":{"id":"2404.19287","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T06:34:21Z","cross_cats_sorted":[],"title_canon_sha256":"7c893851de00fc9fb2007be823d52d8e683a07e310f666d6ebd209473dbab47c","abstract_canon_sha256":"cdc131bf332d2eb4aaa1e113f2e62441e3b448dbdb7e6875073408c20b4129ae"},"schema_version":"1.0"},"canonical_sha256":"c01f2dff7195da61168b0dbc107a18b53106812df7242f98efbe9ffab4a27082","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:13.337661Z","signature_b64":"0qXA6KyraP1tVwsYx7yrYsebS2oKwuP7guyuUWLR78cxgoFrhRs5Pponw8T0mcz6AjKxr20d1VSKLTZYsjd/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c01f2dff7195da61168b0dbc107a18b53106812df7242f98efbe9ffab4a27082","last_reissued_at":"2026-07-05T09:34:13.337182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:13.337182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.19287","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:34:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5mLLcyVwetHqI2LWrd7967FkZoZf3QFvYf+7bTGp1F8PYEiRcKBgJ7mfX6uLt/ONrZsp/bHYgnohbP3kD3tVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:32:01.479571Z"},"content_sha256":"e25d70d42fbfc345a8dc2bf9df3bebf4004eaaf15c15202646bfe4b182eeeb57","schema_version":"1.0","event_id":"sha256:e25d70d42fbfc345a8dc2bf9df3bebf4004eaaf15c15202646bfe4b182eeeb57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YAPS373RSXNGCFULBW6BA6QYWU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Badong Chen, Danilo P. Mandic, Qibin Zhao, Shuanghao Bai, Wanqi Zhou","submitted_at":"2024-04-30T06:34:21Z","abstract_excerpt":"Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primarily focused on enhancing the robustness of image encoders against image-based attacks, with defenses against text-based and multimodal attacks remaining largely unexplored. To this end, this work presents the first comprehensive study on improving the adversarial robustness of VLMs against attacks targeting image, text, and multimodal inputs. This is achieved by proposing multimo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19287","kind":"arxiv","version":3},"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/2404.19287/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":"2026-07-05T09:34:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6EktPPr364MeM/c8IH8XXwpM23MA9cYKOAUvf5/9DPIbVmIn+uUIGC5p2CrAM10VCLuhjT+WLisFEnRiLPNZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:32:01.480489Z"},"content_sha256":"53febae85b4dab6da1bc6d6ebced729c8ecca55a21d6dad1e87f23ffd63ef67b","schema_version":"1.0","event_id":"sha256:53febae85b4dab6da1bc6d6ebced729c8ecca55a21d6dad1e87f23ffd63ef67b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YAPS373RSXNGCFULBW6BA6QYWU/bundle.json","state_url":"https://pith.science/pith/YAPS373RSXNGCFULBW6BA6QYWU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YAPS373RSXNGCFULBW6BA6QYWU/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":"2026-08-09T05:32:01Z","links":{"resolver":"https://pith.science/pith/YAPS373RSXNGCFULBW6BA6QYWU","bundle":"https://pith.science/pith/YAPS373RSXNGCFULBW6BA6QYWU/bundle.json","state":"https://pith.science/pith/YAPS373RSXNGCFULBW6BA6QYWU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YAPS373RSXNGCFULBW6BA6QYWU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YAPS373RSXNGCFULBW6BA6QYWU","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":"cdc131bf332d2eb4aaa1e113f2e62441e3b448dbdb7e6875073408c20b4129ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T06:34:21Z","title_canon_sha256":"7c893851de00fc9fb2007be823d52d8e683a07e310f666d6ebd209473dbab47c"},"schema_version":"1.0","source":{"id":"2404.19287","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.19287","created_at":"2026-07-05T09:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"2404.19287v3","created_at":"2026-07-05T09:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19287","created_at":"2026-07-05T09:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"YAPS373RSXNG","created_at":"2026-07-05T09:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"YAPS373RSXNGCFUL","created_at":"2026-07-05T09:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"YAPS373R","created_at":"2026-07-05T09:34:13Z"}],"graph_snapshots":[{"event_id":"sha256:53febae85b4dab6da1bc6d6ebced729c8ecca55a21d6dad1e87f23ffd63ef67b","target":"graph","created_at":"2026-07-05T09:34:13Z","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/2404.19287/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primarily focused on enhancing the robustness of image encoders against image-based attacks, with defenses against text-based and multimodal attacks remaining largely unexplored. To this end, this work presents the first comprehensive study on improving the adversarial robustness of VLMs against attacks targeting image, text, and multimodal inputs. This is achieved by proposing multimo","authors_text":"Badong Chen, Danilo P. Mandic, Qibin Zhao, Shuanghao Bai, Wanqi Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T06:34:21Z","title":"Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19287","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:e25d70d42fbfc345a8dc2bf9df3bebf4004eaaf15c15202646bfe4b182eeeb57","target":"record","created_at":"2026-07-05T09:34:13Z","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":"cdc131bf332d2eb4aaa1e113f2e62441e3b448dbdb7e6875073408c20b4129ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-30T06:34:21Z","title_canon_sha256":"7c893851de00fc9fb2007be823d52d8e683a07e310f666d6ebd209473dbab47c"},"schema_version":"1.0","source":{"id":"2404.19287","kind":"arxiv","version":3}},"canonical_sha256":"c01f2dff7195da61168b0dbc107a18b53106812df7242f98efbe9ffab4a27082","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c01f2dff7195da61168b0dbc107a18b53106812df7242f98efbe9ffab4a27082","first_computed_at":"2026-07-05T09:34:13.337182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:13.337182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0qXA6KyraP1tVwsYx7yrYsebS2oKwuP7guyuUWLR78cxgoFrhRs5Pponw8T0mcz6AjKxr20d1VSKLTZYsjd/DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:13.337661Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.19287","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e25d70d42fbfc345a8dc2bf9df3bebf4004eaaf15c15202646bfe4b182eeeb57","sha256:53febae85b4dab6da1bc6d6ebced729c8ecca55a21d6dad1e87f23ffd63ef67b"],"state_sha256":"416ac9ff35549a5007010fdacfe4f469ffff6aa12be72ac9f2d4623cee637c60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zey5SX6WdJWAvqQJHHrEqU/CzNp1Olr2rtLU4DXR9ViTetuoCdiNGeuNgR3eLOc4GWJRcD8zIzACZo/n4EIKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:32:01.487076Z","bundle_sha256":"ad160684754d874f580ad00a3b46889f07668166803d7aea6349b963a2d03366"}}