{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KMZEALZXQY2VPHX6CZOIHQK4II","short_pith_number":"pith:KMZEALZX","canonical_record":{"source":{"id":"2402.11083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-16T21:17:42Z","cross_cats_sorted":[],"title_canon_sha256":"2863e53839859ba82cb0146a3f577262b9d77c79a34e3ab9c558b3fd3bb9db14","abstract_canon_sha256":"bc3fcea9671c9eb8fc2a89a5df31eb0fc3cce1a115677fd861f2ad197210b41e"},"schema_version":"1.0"},"canonical_sha256":"5332402f378635579efe165c83c15c4202e546c966004fc68e1db947566c74a0","source":{"kind":"arxiv","id":"2402.11083","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11083","created_at":"2026-07-05T07:46:33Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11083v1","created_at":"2026-07-05T07:46:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11083","created_at":"2026-07-05T07:46:33Z"},{"alias_kind":"pith_short_12","alias_value":"KMZEALZXQY2V","created_at":"2026-07-05T07:46:33Z"},{"alias_kind":"pith_short_16","alias_value":"KMZEALZXQY2VPHX6","created_at":"2026-07-05T07:46:33Z"},{"alias_kind":"pith_short_8","alias_value":"KMZEALZX","created_at":"2026-07-05T07:46:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KMZEALZXQY2VPHX6CZOIHQK4II","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11083","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-16T21:17:42Z","cross_cats_sorted":[],"title_canon_sha256":"2863e53839859ba82cb0146a3f577262b9d77c79a34e3ab9c558b3fd3bb9db14","abstract_canon_sha256":"bc3fcea9671c9eb8fc2a89a5df31eb0fc3cce1a115677fd861f2ad197210b41e"},"schema_version":"1.0"},"canonical_sha256":"5332402f378635579efe165c83c15c4202e546c966004fc68e1db947566c74a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:33.917597Z","signature_b64":"I2L9wW68IpHPsJCNZ0xdI6r7d72ZePRejwSMl/5ZsuFuyVNPH0ExHrmbFGT+6Nd+bfnkGEbKlZoHDRLg96a4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5332402f378635579efe165c83c15c4202e546c966004fc68e1db947566c74a0","last_reissued_at":"2026-07-05T07:46:33.917025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:33.917025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11083","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":"2026-07-05T07:46:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"grwZOk0INj+svHrl2iJC8903kyFvKaMmNPyeBg4P2hLsGuYUdaqVCkVhot9f2ta4s8NRnGVOaRZpQmi2zkGUCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:24:19.269829Z"},"content_sha256":"f691bdc8ac9b7ae665a9b094e179780833d0fdfc607e8bb84d6fc603863ff4de","schema_version":"1.0","event_id":"sha256:f691bdc8ac9b7ae665a9b094e179780833d0fdfc607e8bb84d6fc603863ff4de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KMZEALZXQY2VPHX6CZOIHQK4II","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fenglong Ma, Han Liu, Jiaqi Wang, Jinghui Chen, Muchao Ye, Tianrong Zhang, Ting Wang, Ziyi Yin","submitted_at":"2024-02-16T21:17:42Z","abstract_excerpt":"Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the ``pre-training & finetuning'' learning paradigm significantly improves the VQA performance, the adversarial robustness of such a learning paradigm has not been explored. In this paper, we delve into a new problem: using a pre-trained multimodal source model to create adversarial image-text pairs and then transferring them to attack the target VQA models. Correspondingly, we propose a novel VQAttack model, which can iteratively generate both image and text perturbations wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11083","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/2402.11083/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":"2026-07-05T07:46:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wz0khS7tnaFacMZf+DoxuyVZTwlaHH9rDuPJkvwitwP5GZ9kjlL8kAvNtFJiJHZ8T/vuwb6sI+RAnPbWRSfACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:24:19.270491Z"},"content_sha256":"0c92a9363ede9610990bb2556947d6af1ddbb4d89bd7061f3b6d65abdb53b834","schema_version":"1.0","event_id":"sha256:0c92a9363ede9610990bb2556947d6af1ddbb4d89bd7061f3b6d65abdb53b834"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II/bundle.json","state_url":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KMZEALZXQY2VPHX6CZOIHQK4II/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":"2026-08-12T12:24:19Z","links":{"resolver":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II","bundle":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II/bundle.json","state":"https://pith.science/pith/KMZEALZXQY2VPHX6CZOIHQK4II/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KMZEALZXQY2VPHX6CZOIHQK4II/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KMZEALZXQY2VPHX6CZOIHQK4II","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":"bc3fcea9671c9eb8fc2a89a5df31eb0fc3cce1a115677fd861f2ad197210b41e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-16T21:17:42Z","title_canon_sha256":"2863e53839859ba82cb0146a3f577262b9d77c79a34e3ab9c558b3fd3bb9db14"},"schema_version":"1.0","source":{"id":"2402.11083","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11083","created_at":"2026-07-05T07:46:33Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11083v1","created_at":"2026-07-05T07:46:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11083","created_at":"2026-07-05T07:46:33Z"},{"alias_kind":"pith_short_12","alias_value":"KMZEALZXQY2V","created_at":"2026-07-05T07:46:33Z"},{"alias_kind":"pith_short_16","alias_value":"KMZEALZXQY2VPHX6","created_at":"2026-07-05T07:46:33Z"},{"alias_kind":"pith_short_8","alias_value":"KMZEALZX","created_at":"2026-07-05T07:46:33Z"}],"graph_snapshots":[{"event_id":"sha256:0c92a9363ede9610990bb2556947d6af1ddbb4d89bd7061f3b6d65abdb53b834","target":"graph","created_at":"2026-07-05T07:46:33Z","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/2402.11083/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the ``pre-training & finetuning'' learning paradigm significantly improves the VQA performance, the adversarial robustness of such a learning paradigm has not been explored. In this paper, we delve into a new problem: using a pre-trained multimodal source model to create adversarial image-text pairs and then transferring them to attack the target VQA models. Correspondingly, we propose a novel VQAttack model, which can iteratively generate both image and text perturbations wit","authors_text":"Fenglong Ma, Han Liu, Jiaqi Wang, Jinghui Chen, Muchao Ye, Tianrong Zhang, Ting Wang, Ziyi Yin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-16T21:17:42Z","title":"VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11083","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:f691bdc8ac9b7ae665a9b094e179780833d0fdfc607e8bb84d6fc603863ff4de","target":"record","created_at":"2026-07-05T07:46:33Z","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":"bc3fcea9671c9eb8fc2a89a5df31eb0fc3cce1a115677fd861f2ad197210b41e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-16T21:17:42Z","title_canon_sha256":"2863e53839859ba82cb0146a3f577262b9d77c79a34e3ab9c558b3fd3bb9db14"},"schema_version":"1.0","source":{"id":"2402.11083","kind":"arxiv","version":1}},"canonical_sha256":"5332402f378635579efe165c83c15c4202e546c966004fc68e1db947566c74a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5332402f378635579efe165c83c15c4202e546c966004fc68e1db947566c74a0","first_computed_at":"2026-07-05T07:46:33.917025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:33.917025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I2L9wW68IpHPsJCNZ0xdI6r7d72ZePRejwSMl/5ZsuFuyVNPH0ExHrmbFGT+6Nd+bfnkGEbKlZoHDRLg96a4Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:33.917597Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11083","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f691bdc8ac9b7ae665a9b094e179780833d0fdfc607e8bb84d6fc603863ff4de","sha256:0c92a9363ede9610990bb2556947d6af1ddbb4d89bd7061f3b6d65abdb53b834"],"state_sha256":"afd7edbb7af0d842041b9484fa3212d4b5e9bb3109f45a156eb8f5c138261255"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SRpqgMQQBtpV+yq7yOm9djYCFmqcXNmjQot4ojLxlz612YBiHXb71bczHRWl7Jje/lQHMS9u7Gqe39Wndvk7Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T12:24:19.275894Z","bundle_sha256":"4878a23b746e5bc6a742eb2629f58539fe6fd485cad31cbcd8326af098fa8845"}}