{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KSABIKIGFEAODDKWSEU4UE5HNG","short_pith_number":"pith:KSABIKIG","schema_version":"1.0","canonical_sha256":"54801429062900e18d569129ca13a769b2c6115a5e1a81d3cc072502bd637e30","source":{"kind":"arxiv","id":"2503.10081","version":1},"attestation_state":"computed","paper":{"title":"AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Joonsung Jeon, Sooel Son, Suhyeon Ha, Sung-Eui Yoon, Woo Jae Kim","submitted_at":"2025-03-13T06:05:40Z","abstract_excerpt":"The outstanding capability of diffusion models in generating high-quality images poses significant threats when misused by adversaries. In particular, we assume malicious adversaries exploiting diffusion models for inpainting tasks, such as replacing a specific region with a celebrity. While existing methods for protecting images from manipulation in diffusion-based generative models have primarily focused on image-to-image and text-to-image tasks, the challenge of preventing unauthorized inpainting has been rarely addressed, often resulting in suboptimal protection performance. To mitigate in"},"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":"2503.10081","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T06:05:40Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"a0c0981b9c727036e68b0f3d159f0d0eb8677b29db4d6e1f36166586bfd39318","abstract_canon_sha256":"00c13ce66ba8883e7d6380e3d6593796c2934e872fd11e2839cc6c9926bfda28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:38.035287Z","signature_b64":"E3GLawMzG9vjE1KxPtH2yPJfv5WM+CytYAPRKVCyupD7EYxx3FDl5D6Vk8g+jMJSKVjS/L+yxHyvYnM2q0trBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54801429062900e18d569129ca13a769b2c6115a5e1a81d3cc072502bd637e30","last_reissued_at":"2026-07-05T10:30:38.034257Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:38.034257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CV","authors_text":"Joonsung Jeon, Sooel Son, Suhyeon Ha, Sung-Eui Yoon, Woo Jae Kim","submitted_at":"2025-03-13T06:05:40Z","abstract_excerpt":"The outstanding capability of diffusion models in generating high-quality images poses significant threats when misused by adversaries. In particular, we assume malicious adversaries exploiting diffusion models for inpainting tasks, such as replacing a specific region with a celebrity. While existing methods for protecting images from manipulation in diffusion-based generative models have primarily focused on image-to-image and text-to-image tasks, the challenge of preventing unauthorized inpainting has been rarely addressed, often resulting in suboptimal protection performance. To mitigate in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10081","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/2503.10081/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":"2503.10081","created_at":"2026-07-05T10:30:38.034447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10081v1","created_at":"2026-07-05T10:30:38.034447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10081","created_at":"2026-07-05T10:30:38.034447+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSABIKIGFEAO","created_at":"2026-07-05T10:30:38.034447+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSABIKIGFEAODDKW","created_at":"2026-07-05T10:30:38.034447+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSABIKIG","created_at":"2026-07-05T10:30:38.034447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.16223","citing_title":"Dac-Fake: A Divide and Conquer Framework for Detecting Fake News on Social Media","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSABIKIGFEAODDKWSEU4UE5HNG","json":"https://pith.science/pith/KSABIKIGFEAODDKWSEU4UE5HNG.json","graph_json":"https://pith.science/api/pith-number/KSABIKIGFEAODDKWSEU4UE5HNG/graph.json","events_json":"https://pith.science/api/pith-number/KSABIKIGFEAODDKWSEU4UE5HNG/events.json","paper":"https://pith.science/paper/KSABIKIG"},"agent_actions":{"view_html":"https://pith.science/pith/KSABIKIGFEAODDKWSEU4UE5HNG","download_json":"https://pith.science/pith/KSABIKIGFEAODDKWSEU4UE5HNG.json","view_paper":"https://pith.science/paper/KSABIKIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10081&json=true","fetch_graph":"https://pith.science/api/pith-number/KSABIKIGFEAODDKWSEU4UE5HNG/graph.json","fetch_events":"https://pith.science/api/pith-number/KSABIKIGFEAODDKWSEU4UE5HNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSABIKIGFEAODDKWSEU4UE5HNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSABIKIGFEAODDKWSEU4UE5HNG/action/storage_attestation","attest_author":"https://pith.science/pith/KSABIKIGFEAODDKWSEU4UE5HNG/action/author_attestation","sign_citation":"https://pith.science/pith/KSABIKIGFEAODDKWSEU4UE5HNG/action/citation_signature","submit_replication":"https://pith.science/pith/KSABIKIGFEAODDKWSEU4UE5HNG/action/replication_record"}},"created_at":"2026-07-05T10:30:38.034447+00:00","updated_at":"2026-07-05T10:30:38.034447+00:00"}