{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4V4A3TPALZGBPFYSNBPRCY2JL7","short_pith_number":"pith:4V4A3TPA","schema_version":"1.0","canonical_sha256":"e5780dcde05e4c179712685f1163495fcf3c643371a4670ab5c0bacc9a4e14df","source":{"kind":"arxiv","id":"2304.11285","version":1},"attestation_state":"computed","paper":{"title":"Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Andreas Rauber, Isabell Lederer, Rudolf Mayer","submitted_at":"2023-04-22T01:05:48Z","abstract_excerpt":"The commercial use of Machine Learning (ML) is spreading; at the same time, ML models are becoming more complex and more expensive to train, which makes Intellectual Property Protection (IPP) of trained models a pressing issue. Unlike other domains that can build on a solid understanding of the threats, attacks and defenses available to protect their IP, the ML-related research in this regard is still very fragmented. This is also due to a missing unified view as well as a common taxonomy of these aspects.\n  In this paper, we systematize our findings on IPP in ML, while focusing on threats and"},"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":"2304.11285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-22T01:05:48Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"2c95b58d32f17fff2f31196cb1c985bc9ba474f41139cefe93e0ac581461b9d7","abstract_canon_sha256":"ff0775bacd9ae3d77bffa8e82e302d55ca0119bda9c30bf8216ef329925350f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:38.510729Z","signature_b64":"eWSbv1JUOznxcx9J3OuJn/O1jHyQmbR+dIcDhxxevhlIOkVK3DXrVOYIySkd1H9DF4KKD6eBJ5x6/BzTjXsaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5780dcde05e4c179712685f1163495fcf3c643371a4670ab5c0bacc9a4e14df","last_reissued_at":"2026-07-05T06:04:38.510403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:38.510403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Andreas Rauber, Isabell Lederer, Rudolf Mayer","submitted_at":"2023-04-22T01:05:48Z","abstract_excerpt":"The commercial use of Machine Learning (ML) is spreading; at the same time, ML models are becoming more complex and more expensive to train, which makes Intellectual Property Protection (IPP) of trained models a pressing issue. Unlike other domains that can build on a solid understanding of the threats, attacks and defenses available to protect their IP, the ML-related research in this regard is still very fragmented. This is also due to a missing unified view as well as a common taxonomy of these aspects.\n  In this paper, we systematize our findings on IPP in ML, while focusing on threats and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11285","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/2304.11285/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":"2304.11285","created_at":"2026-07-05T06:04:38.510454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11285v1","created_at":"2026-07-05T06:04:38.510454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11285","created_at":"2026-07-05T06:04:38.510454+00:00"},{"alias_kind":"pith_short_12","alias_value":"4V4A3TPALZGB","created_at":"2026-07-05T06:04:38.510454+00:00"},{"alias_kind":"pith_short_16","alias_value":"4V4A3TPALZGBPFYS","created_at":"2026-07-05T06:04:38.510454+00:00"},{"alias_kind":"pith_short_8","alias_value":"4V4A3TPA","created_at":"2026-07-05T06:04:38.510454+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/4V4A3TPALZGBPFYSNBPRCY2JL7","json":"https://pith.science/pith/4V4A3TPALZGBPFYSNBPRCY2JL7.json","graph_json":"https://pith.science/api/pith-number/4V4A3TPALZGBPFYSNBPRCY2JL7/graph.json","events_json":"https://pith.science/api/pith-number/4V4A3TPALZGBPFYSNBPRCY2JL7/events.json","paper":"https://pith.science/paper/4V4A3TPA"},"agent_actions":{"view_html":"https://pith.science/pith/4V4A3TPALZGBPFYSNBPRCY2JL7","download_json":"https://pith.science/pith/4V4A3TPALZGBPFYSNBPRCY2JL7.json","view_paper":"https://pith.science/paper/4V4A3TPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11285&json=true","fetch_graph":"https://pith.science/api/pith-number/4V4A3TPALZGBPFYSNBPRCY2JL7/graph.json","fetch_events":"https://pith.science/api/pith-number/4V4A3TPALZGBPFYSNBPRCY2JL7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4V4A3TPALZGBPFYSNBPRCY2JL7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4V4A3TPALZGBPFYSNBPRCY2JL7/action/storage_attestation","attest_author":"https://pith.science/pith/4V4A3TPALZGBPFYSNBPRCY2JL7/action/author_attestation","sign_citation":"https://pith.science/pith/4V4A3TPALZGBPFYSNBPRCY2JL7/action/citation_signature","submit_replication":"https://pith.science/pith/4V4A3TPALZGBPFYSNBPRCY2JL7/action/replication_record"}},"created_at":"2026-07-05T06:04:38.510454+00:00","updated_at":"2026-07-05T06:04:38.510454+00:00"}