{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:R5X7BHFVPDZP2IJ2E7S43FZIYR","short_pith_number":"pith:R5X7BHFV","canonical_record":{"source":{"id":"2106.04267","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T11:54:51Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"353eefdc17021e05d5e8d197afec47b53f4c4496e1e756c8524f9edeae0a9723","abstract_canon_sha256":"a28fddcb70962b610d6f6a446a6c883ef9e4737473473ee812bfc6a35e39cf43"},"schema_version":"1.0"},"canonical_sha256":"8f6ff09cb578f2fd213a27e5cd9728c471f4460d13aa71545edceca9ef65c0b9","source":{"kind":"arxiv","id":"2106.04267","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.04267","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"arxiv_version","alias_value":"2106.04267v1","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04267","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"pith_short_12","alias_value":"R5X7BHFVPDZP","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"pith_short_16","alias_value":"R5X7BHFVPDZP2IJ2","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"pith_short_8","alias_value":"R5X7BHFV","created_at":"2026-07-05T04:15:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:R5X7BHFVPDZP2IJ2E7S43FZIYR","target":"record","payload":{"canonical_record":{"source":{"id":"2106.04267","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T11:54:51Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"353eefdc17021e05d5e8d197afec47b53f4c4496e1e756c8524f9edeae0a9723","abstract_canon_sha256":"a28fddcb70962b610d6f6a446a6c883ef9e4737473473ee812bfc6a35e39cf43"},"schema_version":"1.0"},"canonical_sha256":"8f6ff09cb578f2fd213a27e5cd9728c471f4460d13aa71545edceca9ef65c0b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:27.479497Z","signature_b64":"4dHSzZ+v3WZBVuDRArr/Uz5qN168lIZh6Jhy0jtQC3Sd/FodbdhHKhfSOAKU/7vNhCs+Bg1dRPmiVbsNwWcBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f6ff09cb578f2fd213a27e5cd9728c471f4460d13aa71545edceca9ef65c0b9","last_reissued_at":"2026-07-05T04:15:27.478983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:27.478983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.04267","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:15:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MTBQYnthd5VES5U/Tn7S5WoXXL7ZDc++XAef5K7t5Dl093b/SThot9VEZ+NzqePAmud7MbvNreKyeeAiZEDZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:30:07.425598Z"},"content_sha256":"398c8516ee0595bb4d017df239304eb3e8093a2aa4dcd436ba54da1f0ff9a478","schema_version":"1.0","event_id":"sha256:398c8516ee0595bb4d017df239304eb3e8093a2aa4dcd436ba54da1f0ff9a478"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:R5X7BHFVPDZP2IJ2E7S43FZIYR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Supervised Machine Learning with Plausible Deniability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Jasmin Wachter, Manuel Egger, Manuel Hobisch, Sandra K\\\"onig, Stefan Rass","submitted_at":"2021-06-08T11:54:51Z","abstract_excerpt":"We study the question of how well machine learning (ML) models trained on a certain data set provide privacy for the training data, or equivalently, whether it is possible to reverse-engineer the training data from a given ML model. While this is easy to answer negatively in the most general case, it is interesting to note that the protection extends over non-recoverability towards plausible deniability: Given an ML model $f$, we show that one can take a set of purely random training data, and from this define a suitable ``learning rule'' that will produce a ML model that is exactly $f$. Thus,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04267","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/2106.04267/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:15:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zG6Xn2F5HCGO/tvdcXMnPWDiBGbImIk9JfepznDLL90vJ2cLbZGwIsl3K1lSH0JqhfPquxYQ00slNPiSCMsTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:30:07.426489Z"},"content_sha256":"3b169bbbd1771d3bfad4d414b6420e72a3ebd2b13bddba9f028751c1a081699e","schema_version":"1.0","event_id":"sha256:3b169bbbd1771d3bfad4d414b6420e72a3ebd2b13bddba9f028751c1a081699e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R5X7BHFVPDZP2IJ2E7S43FZIYR/bundle.json","state_url":"https://pith.science/pith/R5X7BHFVPDZP2IJ2E7S43FZIYR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R5X7BHFVPDZP2IJ2E7S43FZIYR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T23:30:07Z","links":{"resolver":"https://pith.science/pith/R5X7BHFVPDZP2IJ2E7S43FZIYR","bundle":"https://pith.science/pith/R5X7BHFVPDZP2IJ2E7S43FZIYR/bundle.json","state":"https://pith.science/pith/R5X7BHFVPDZP2IJ2E7S43FZIYR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R5X7BHFVPDZP2IJ2E7S43FZIYR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:R5X7BHFVPDZP2IJ2E7S43FZIYR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a28fddcb70962b610d6f6a446a6c883ef9e4737473473ee812bfc6a35e39cf43","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T11:54:51Z","title_canon_sha256":"353eefdc17021e05d5e8d197afec47b53f4c4496e1e756c8524f9edeae0a9723"},"schema_version":"1.0","source":{"id":"2106.04267","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.04267","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"arxiv_version","alias_value":"2106.04267v1","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04267","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"pith_short_12","alias_value":"R5X7BHFVPDZP","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"pith_short_16","alias_value":"R5X7BHFVPDZP2IJ2","created_at":"2026-07-05T04:15:27Z"},{"alias_kind":"pith_short_8","alias_value":"R5X7BHFV","created_at":"2026-07-05T04:15:27Z"}],"graph_snapshots":[{"event_id":"sha256:3b169bbbd1771d3bfad4d414b6420e72a3ebd2b13bddba9f028751c1a081699e","target":"graph","created_at":"2026-07-05T04:15:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.04267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the question of how well machine learning (ML) models trained on a certain data set provide privacy for the training data, or equivalently, whether it is possible to reverse-engineer the training data from a given ML model. While this is easy to answer negatively in the most general case, it is interesting to note that the protection extends over non-recoverability towards plausible deniability: Given an ML model $f$, we show that one can take a set of purely random training data, and from this define a suitable ``learning rule'' that will produce a ML model that is exactly $f$. Thus,","authors_text":"Jasmin Wachter, Manuel Egger, Manuel Hobisch, Sandra K\\\"onig, Stefan Rass","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T11:54:51Z","title":"Supervised Machine Learning with Plausible Deniability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04267","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:398c8516ee0595bb4d017df239304eb3e8093a2aa4dcd436ba54da1f0ff9a478","target":"record","created_at":"2026-07-05T04:15:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a28fddcb70962b610d6f6a446a6c883ef9e4737473473ee812bfc6a35e39cf43","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T11:54:51Z","title_canon_sha256":"353eefdc17021e05d5e8d197afec47b53f4c4496e1e756c8524f9edeae0a9723"},"schema_version":"1.0","source":{"id":"2106.04267","kind":"arxiv","version":1}},"canonical_sha256":"8f6ff09cb578f2fd213a27e5cd9728c471f4460d13aa71545edceca9ef65c0b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f6ff09cb578f2fd213a27e5cd9728c471f4460d13aa71545edceca9ef65c0b9","first_computed_at":"2026-07-05T04:15:27.478983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:27.478983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4dHSzZ+v3WZBVuDRArr/Uz5qN168lIZh6Jhy0jtQC3Sd/FodbdhHKhfSOAKU/7vNhCs+Bg1dRPmiVbsNwWcBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:27.479497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.04267","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:398c8516ee0595bb4d017df239304eb3e8093a2aa4dcd436ba54da1f0ff9a478","sha256:3b169bbbd1771d3bfad4d414b6420e72a3ebd2b13bddba9f028751c1a081699e"],"state_sha256":"aca5136baafa4adea387145651a1077342537dfe72e824574e76863533bef20c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x6UyYBT6WwVPWrU+4kYMGXEw18aqMIAJrQI2tVgqhUzT0JvyMyL6awrYbrfw8IqKxOy1UH4Hsz4E+GfncRt6AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:30:07.432237Z","bundle_sha256":"9f9899a73ae74d075a1757f52cd214a519b2982c3a189765eb4af080e058352a"}}