{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YTWIMGOFM3AMGINRJ2UWCBSGXG","short_pith_number":"pith:YTWIMGOF","schema_version":"1.0","canonical_sha256":"c4ec8619c566c0c321b14ea9610646b9bafc99e284ce7d8e7c9298e2184a2fb6","source":{"kind":"arxiv","id":"2602.14679","version":2},"attestation_state":"computed","paper":{"title":"Universal Image Immunization against Diffusion-based Image Editing via Semantic Injection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chanhui Lee, Donggyu Choi, Hae-Gon Jeon, Jeany Son, Seunghyun Shin","submitted_at":"2026-02-16T12:08:37Z","abstract_excerpt":"Diffusion model advances have enabled powerful text-guided image editing, but also raise ethical and legal risks such as deepfakes and unauthorized use. To prevent these risks, adversarial attack-based image immunization has emerged as a promising defense against AI-driven semantic manipulation. Yet, most existing approaches require image-specific optimization or additional neural networks at inference time, hindering scalability and practicality. In this paper, we propose the first universal adversarial perturbation-based image immunization framework that generates a single, image-agnostic ad"},"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":"2602.14679","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-16T12:08:37Z","cross_cats_sorted":[],"title_canon_sha256":"15a0e55034d75a3b48f0dde5a77e6db1c7dbe3f834fb2da96bf7479636d1e79b","abstract_canon_sha256":"74e00f2345f1186e02665d8fd55540075db3216b55336ba4972de89c98663942"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:28.110726Z","signature_b64":"jDo1+nyxonz2myKyu9fuylc6xU5HTw2oUu5+LlXPYQqqy8X6W4nP5HFySoBBVb/w3DOEEjeHO+Sqs7oLA5kVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4ec8619c566c0c321b14ea9610646b9bafc99e284ce7d8e7c9298e2184a2fb6","last_reissued_at":"2026-07-02T01:17:28.110228Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:28.110228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Image Immunization against Diffusion-based Image Editing via Semantic Injection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chanhui Lee, Donggyu Choi, Hae-Gon Jeon, Jeany Son, Seunghyun Shin","submitted_at":"2026-02-16T12:08:37Z","abstract_excerpt":"Diffusion model advances have enabled powerful text-guided image editing, but also raise ethical and legal risks such as deepfakes and unauthorized use. To prevent these risks, adversarial attack-based image immunization has emerged as a promising defense against AI-driven semantic manipulation. Yet, most existing approaches require image-specific optimization or additional neural networks at inference time, hindering scalability and practicality. In this paper, we propose the first universal adversarial perturbation-based image immunization framework that generates a single, image-agnostic ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14679","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/2602.14679/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":"2602.14679","created_at":"2026-07-02T01:17:28.110280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.14679v2","created_at":"2026-07-02T01:17:28.110280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14679","created_at":"2026-07-02T01:17:28.110280+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTWIMGOFM3AM","created_at":"2026-07-02T01:17:28.110280+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTWIMGOFM3AMGINR","created_at":"2026-07-02T01:17:28.110280+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTWIMGOF","created_at":"2026-07-02T01:17:28.110280+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.01499","citing_title":"Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19398","citing_title":"Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTWIMGOFM3AMGINRJ2UWCBSGXG","json":"https://pith.science/pith/YTWIMGOFM3AMGINRJ2UWCBSGXG.json","graph_json":"https://pith.science/api/pith-number/YTWIMGOFM3AMGINRJ2UWCBSGXG/graph.json","events_json":"https://pith.science/api/pith-number/YTWIMGOFM3AMGINRJ2UWCBSGXG/events.json","paper":"https://pith.science/paper/YTWIMGOF"},"agent_actions":{"view_html":"https://pith.science/pith/YTWIMGOFM3AMGINRJ2UWCBSGXG","download_json":"https://pith.science/pith/YTWIMGOFM3AMGINRJ2UWCBSGXG.json","view_paper":"https://pith.science/paper/YTWIMGOF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.14679&json=true","fetch_graph":"https://pith.science/api/pith-number/YTWIMGOFM3AMGINRJ2UWCBSGXG/graph.json","fetch_events":"https://pith.science/api/pith-number/YTWIMGOFM3AMGINRJ2UWCBSGXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTWIMGOFM3AMGINRJ2UWCBSGXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTWIMGOFM3AMGINRJ2UWCBSGXG/action/storage_attestation","attest_author":"https://pith.science/pith/YTWIMGOFM3AMGINRJ2UWCBSGXG/action/author_attestation","sign_citation":"https://pith.science/pith/YTWIMGOFM3AMGINRJ2UWCBSGXG/action/citation_signature","submit_replication":"https://pith.science/pith/YTWIMGOFM3AMGINRJ2UWCBSGXG/action/replication_record"}},"created_at":"2026-07-02T01:17:28.110280+00:00","updated_at":"2026-07-02T01:17:28.110280+00:00"}