{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5C2QBM3Q4754PIPQNGJQWGA3MM","short_pith_number":"pith:5C2QBM3Q","schema_version":"1.0","canonical_sha256":"e8b500b370e7fbc7a1f069930b181b632231f72ac47f9ed363a98da7b6ea02ab","source":{"kind":"arxiv","id":"2412.05538","version":2},"attestation_state":"computed","paper":{"title":"Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.CV","authors_text":"Erjia Xiao, Hao Cheng, Jiahang Cao, Jiayan Yang, Jindong Gu, Jize Zhang, Kaidi Xu, Qiang Zhang, Renjing Xu","submitted_at":"2024-12-07T04:55:39Z","abstract_excerpt":"Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images containing inappropriate content by simply editing the language modality input. To mitigate this security concern, numerous guarding or defensive strategies have been proposed, with a particular emphasis on safeguarding language modality. However, in practical applications, threats in the vision modality, particularly in tasks involving the editing of real-world ima"},"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":"2412.05538","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-07T04:55:39Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"cd0f3dc6d5b93c066b63a9c8db928ebbb640fc3e5ce2aa669ac804671b97fde6","abstract_canon_sha256":"0106ce4cafa3df2db5f6d57cf839bcca38fd45ae8dd2e39dc9ee5879f18c2efc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:13.038779Z","signature_b64":"QwSfuiwM4qJNHRr0lZWv1VxdQojsmKeupKbMDW3JGN1XXAvfmWXQC8Q7sG/4dEAfG3vQeAUCzzAi0MocMDhZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8b500b370e7fbc7a1f069930b181b632231f72ac47f9ed363a98da7b6ea02ab","last_reissued_at":"2026-07-05T10:56:13.038287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:13.038287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.CV","authors_text":"Erjia Xiao, Hao Cheng, Jiahang Cao, Jiayan Yang, Jindong Gu, Jize Zhang, Kaidi Xu, Qiang Zhang, Renjing Xu","submitted_at":"2024-12-07T04:55:39Z","abstract_excerpt":"Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images containing inappropriate content by simply editing the language modality input. To mitigate this security concern, numerous guarding or defensive strategies have been proposed, with a particular emphasis on safeguarding language modality. However, in practical applications, threats in the vision modality, particularly in tasks involving the editing of real-world ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05538","kind":"arxiv","version":2},"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/2412.05538/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":"2412.05538","created_at":"2026-07-05T10:56:13.038352+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05538v2","created_at":"2026-07-05T10:56:13.038352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05538","created_at":"2026-07-05T10:56:13.038352+00:00"},{"alias_kind":"pith_short_12","alias_value":"5C2QBM3Q4754","created_at":"2026-07-05T10:56:13.038352+00:00"},{"alias_kind":"pith_short_16","alias_value":"5C2QBM3Q4754PIPQ","created_at":"2026-07-05T10:56:13.038352+00:00"},{"alias_kind":"pith_short_8","alias_value":"5C2QBM3Q","created_at":"2026-07-05T10:56:13.038352+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5C2QBM3Q4754PIPQNGJQWGA3MM","json":"https://pith.science/pith/5C2QBM3Q4754PIPQNGJQWGA3MM.json","graph_json":"https://pith.science/api/pith-number/5C2QBM3Q4754PIPQNGJQWGA3MM/graph.json","events_json":"https://pith.science/api/pith-number/5C2QBM3Q4754PIPQNGJQWGA3MM/events.json","paper":"https://pith.science/paper/5C2QBM3Q"},"agent_actions":{"view_html":"https://pith.science/pith/5C2QBM3Q4754PIPQNGJQWGA3MM","download_json":"https://pith.science/pith/5C2QBM3Q4754PIPQNGJQWGA3MM.json","view_paper":"https://pith.science/paper/5C2QBM3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05538&json=true","fetch_graph":"https://pith.science/api/pith-number/5C2QBM3Q4754PIPQNGJQWGA3MM/graph.json","fetch_events":"https://pith.science/api/pith-number/5C2QBM3Q4754PIPQNGJQWGA3MM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5C2QBM3Q4754PIPQNGJQWGA3MM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5C2QBM3Q4754PIPQNGJQWGA3MM/action/storage_attestation","attest_author":"https://pith.science/pith/5C2QBM3Q4754PIPQNGJQWGA3MM/action/author_attestation","sign_citation":"https://pith.science/pith/5C2QBM3Q4754PIPQNGJQWGA3MM/action/citation_signature","submit_replication":"https://pith.science/pith/5C2QBM3Q4754PIPQNGJQWGA3MM/action/replication_record"}},"created_at":"2026-07-05T10:56:13.038352+00:00","updated_at":"2026-07-05T10:56:13.038352+00:00"}