{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X27N5PGNZV4OORRYANF6GCKEEK","short_pith_number":"pith:X27N5PGN","schema_version":"1.0","canonical_sha256":"bebedebccdcd78e74638034be30944228a9fe76925694bf2ac979c2e35bd71b8","source":{"kind":"arxiv","id":"2312.04913","version":1},"attestation_state":"computed","paper":{"title":"SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bangyan He, Siyuan Liang, Tianrui Lou, Xiaochun Cao, Xiaojun Jia, Yang Liu","submitted_at":"2023-12-08T09:08:50Z","abstract_excerpt":"Current Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples. These adversarial examples present substantial security risks to VLP models, as they can leverage inherent weaknesses in the models, resulting in incorrect predictions. In contrast to white-box adversarial attacks, transfer attacks (where the adversary crafts adversarial examples on a white-box model to fool another black-box model) are more reflective of real-world scenarios, thus making them more meaningful for research. By summarizing and analyzing existing research, we identified two factors that can "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.04913","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-08T09:08:50Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"title_canon_sha256":"edef034fc367e0c9f24d00710583281628652e6eeeb9ef2963ec0702a70e1417","abstract_canon_sha256":"2b1d954bef6ed96ec97a46bf86aca35a16c0b845d51c205ff675e64211032d69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:54.230778Z","signature_b64":"FVgo0ot0XcYtCj2U9rCnDNZIkfGQl0tijg0qxkZC/swrU4z5cs12W5wYbhmt6lzxdET0OiW8oRWWy4fdJ/zUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bebedebccdcd78e74638034be30944228a9fe76925694bf2ac979c2e35bd71b8","last_reissued_at":"2026-07-05T07:21:54.230289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:54.230289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bangyan He, Siyuan Liang, Tianrui Lou, Xiaochun Cao, Xiaojun Jia, Yang Liu","submitted_at":"2023-12-08T09:08:50Z","abstract_excerpt":"Current Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples. These adversarial examples present substantial security risks to VLP models, as they can leverage inherent weaknesses in the models, resulting in incorrect predictions. In contrast to white-box adversarial attacks, transfer attacks (where the adversary crafts adversarial examples on a white-box model to fool another black-box model) are more reflective of real-world scenarios, thus making them more meaningful for research. By summarizing and analyzing existing research, we identified two factors that can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04913","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/2312.04913/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.04913","created_at":"2026-07-05T07:21:54.230351+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04913v1","created_at":"2026-07-05T07:21:54.230351+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04913","created_at":"2026-07-05T07:21:54.230351+00:00"},{"alias_kind":"pith_short_12","alias_value":"X27N5PGNZV4O","created_at":"2026-07-05T07:21:54.230351+00:00"},{"alias_kind":"pith_short_16","alias_value":"X27N5PGNZV4OORRY","created_at":"2026-07-05T07:21:54.230351+00:00"},{"alias_kind":"pith_short_8","alias_value":"X27N5PGN","created_at":"2026-07-05T07:21:54.230351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05783","citing_title":"Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective","ref_index":88,"is_internal_anchor":true},{"citing_arxiv_id":"2502.05206","citing_title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","ref_index":223,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17577","citing_title":"TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04630","citing_title":"Multimodal Backdoor Attack on VLMs for Autonomous Driving via Graffiti and Cross-Lingual Triggers","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X27N5PGNZV4OORRYANF6GCKEEK","json":"https://pith.science/pith/X27N5PGNZV4OORRYANF6GCKEEK.json","graph_json":"https://pith.science/api/pith-number/X27N5PGNZV4OORRYANF6GCKEEK/graph.json","events_json":"https://pith.science/api/pith-number/X27N5PGNZV4OORRYANF6GCKEEK/events.json","paper":"https://pith.science/paper/X27N5PGN"},"agent_actions":{"view_html":"https://pith.science/pith/X27N5PGNZV4OORRYANF6GCKEEK","download_json":"https://pith.science/pith/X27N5PGNZV4OORRYANF6GCKEEK.json","view_paper":"https://pith.science/paper/X27N5PGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04913&json=true","fetch_graph":"https://pith.science/api/pith-number/X27N5PGNZV4OORRYANF6GCKEEK/graph.json","fetch_events":"https://pith.science/api/pith-number/X27N5PGNZV4OORRYANF6GCKEEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X27N5PGNZV4OORRYANF6GCKEEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X27N5PGNZV4OORRYANF6GCKEEK/action/storage_attestation","attest_author":"https://pith.science/pith/X27N5PGNZV4OORRYANF6GCKEEK/action/author_attestation","sign_citation":"https://pith.science/pith/X27N5PGNZV4OORRYANF6GCKEEK/action/citation_signature","submit_replication":"https://pith.science/pith/X27N5PGNZV4OORRYANF6GCKEEK/action/replication_record"}},"created_at":"2026-07-05T07:21:54.230351+00:00","updated_at":"2026-07-05T07:21:54.230351+00:00"}