{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M6XSWRBZJNTG7WZPYMVFZ5GYJ6","short_pith_number":"pith:M6XSWRBZ","schema_version":"1.0","canonical_sha256":"67af2b44394b666fdb2fc32a5cf4d84facd3513bbbeda1bab09684bb9ca7b467","source":{"kind":"arxiv","id":"2410.09909","version":1},"attestation_state":"computed","paper":{"title":"UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Tiehua Zhang, Xingjun Ma, Ye Sun, Yu-Gang Jiang","submitted_at":"2024-10-13T16:34:46Z","abstract_excerpt":"Image segmentation is a crucial vision task that groups pixels within an image into semantically meaningful segments, which is pivotal in obtaining a fine-grained understanding of real-world scenes. However, an increasing privacy concern exists regarding training large-scale image segmentation models on unauthorized private data. In this work, we exploit the concept of unlearnable examples to make images unusable to model training by generating and adding unlearnable noise into the original images. Particularly, we propose a novel Unlearnable Segmentation (UnSeg) framework to train a universal"},"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":"2410.09909","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-13T16:34:46Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"267f3928091d0771ec0a57bc124ce5af0d13f29df7b05b01429737cea1597a8b","abstract_canon_sha256":"bf592f899acfb97c105e1416067717c2a2a23e114da6810adfe454c10453a162"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:07.900770Z","signature_b64":"JGDq0L3A6/6swlVx4nvtY8qEKgQmRhwmSWphVf9CIKHGPftmY9NQIT1I4egZA9BGoXpSegMc835jAGNq3NU2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67af2b44394b666fdb2fc32a5cf4d84facd3513bbbeda1bab09684bb9ca7b467","last_reissued_at":"2026-07-05T09:20:07.900342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:07.900342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Zhang, Tiehua Zhang, Xingjun Ma, Ye Sun, Yu-Gang Jiang","submitted_at":"2024-10-13T16:34:46Z","abstract_excerpt":"Image segmentation is a crucial vision task that groups pixels within an image into semantically meaningful segments, which is pivotal in obtaining a fine-grained understanding of real-world scenes. However, an increasing privacy concern exists regarding training large-scale image segmentation models on unauthorized private data. In this work, we exploit the concept of unlearnable examples to make images unusable to model training by generating and adding unlearnable noise into the original images. Particularly, we propose a novel Unlearnable Segmentation (UnSeg) framework to train a universal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09909","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/2410.09909/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":"2410.09909","created_at":"2026-07-05T09:20:07.900398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09909v1","created_at":"2026-07-05T09:20:07.900398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09909","created_at":"2026-07-05T09:20:07.900398+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6XSWRBZJNTG","created_at":"2026-07-05T09:20:07.900398+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6XSWRBZJNTG7WZP","created_at":"2026-07-05T09:20:07.900398+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6XSWRBZ","created_at":"2026-07-05T09:20:07.900398+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/M6XSWRBZJNTG7WZPYMVFZ5GYJ6","json":"https://pith.science/pith/M6XSWRBZJNTG7WZPYMVFZ5GYJ6.json","graph_json":"https://pith.science/api/pith-number/M6XSWRBZJNTG7WZPYMVFZ5GYJ6/graph.json","events_json":"https://pith.science/api/pith-number/M6XSWRBZJNTG7WZPYMVFZ5GYJ6/events.json","paper":"https://pith.science/paper/M6XSWRBZ"},"agent_actions":{"view_html":"https://pith.science/pith/M6XSWRBZJNTG7WZPYMVFZ5GYJ6","download_json":"https://pith.science/pith/M6XSWRBZJNTG7WZPYMVFZ5GYJ6.json","view_paper":"https://pith.science/paper/M6XSWRBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09909&json=true","fetch_graph":"https://pith.science/api/pith-number/M6XSWRBZJNTG7WZPYMVFZ5GYJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/M6XSWRBZJNTG7WZPYMVFZ5GYJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6XSWRBZJNTG7WZPYMVFZ5GYJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6XSWRBZJNTG7WZPYMVFZ5GYJ6/action/storage_attestation","attest_author":"https://pith.science/pith/M6XSWRBZJNTG7WZPYMVFZ5GYJ6/action/author_attestation","sign_citation":"https://pith.science/pith/M6XSWRBZJNTG7WZPYMVFZ5GYJ6/action/citation_signature","submit_replication":"https://pith.science/pith/M6XSWRBZJNTG7WZPYMVFZ5GYJ6/action/replication_record"}},"created_at":"2026-07-05T09:20:07.900398+00:00","updated_at":"2026-07-05T09:20:07.900398+00:00"}