{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZHZ4P5XWMOHOAUL7PRTMTRZ65Z","short_pith_number":"pith:ZHZ4P5XW","canonical_record":{"source":{"id":"2012.01791","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-03T09:47:47Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"51c1bd1a62855ae597266b2c19f92af631c9f064298cd2bef43f1984a45d96a8","abstract_canon_sha256":"18401c770367c6d76d325af2cca5d9191637e5fa28da692d8bc6098d93a340ef"},"schema_version":"1.0"},"canonical_sha256":"c9f3c7f6f6638ee0517f7c66c9c73eee4b6c0b78a56e15bf9b7f22ec2c3a0087","source":{"kind":"arxiv","id":"2012.01791","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.01791","created_at":"2026-07-05T01:56:50Z"},{"alias_kind":"arxiv_version","alias_value":"2012.01791v1","created_at":"2026-07-05T01:56:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.01791","created_at":"2026-07-05T01:56:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZHZ4P5XWMOHO","created_at":"2026-07-05T01:56:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZHZ4P5XWMOHOAUL7","created_at":"2026-07-05T01:56:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZHZ4P5XW","created_at":"2026-07-05T01:56:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZHZ4P5XWMOHOAUL7PRTMTRZ65Z","target":"record","payload":{"canonical_record":{"source":{"id":"2012.01791","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-03T09:47:47Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"51c1bd1a62855ae597266b2c19f92af631c9f064298cd2bef43f1984a45d96a8","abstract_canon_sha256":"18401c770367c6d76d325af2cca5d9191637e5fa28da692d8bc6098d93a340ef"},"schema_version":"1.0"},"canonical_sha256":"c9f3c7f6f6638ee0517f7c66c9c73eee4b6c0b78a56e15bf9b7f22ec2c3a0087","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:50.201221Z","signature_b64":"CtYi5LpMN4RHXdCzCE1UifYPmtjZEGu2xym9igrU2VNSfpu0VsgiQXqRvRyAsYuHhwD3COYLDU7+TVODwD6NAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9f3c7f6f6638ee0517f7c66c9c73eee4b6c0b78a56e15bf9b7f22ec2c3a0087","last_reissued_at":"2026-07-05T01:56:50.200872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:50.200872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.01791","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":"2026-07-05T01:56:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DjKHONLtR/AuIySCXXT6+JxUdaiagxNwRP3/57gCnOm5nZ/s0YNTqFXu54e14N9yepBHdQM6cDYRAkIufGdTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:51:55.230347Z"},"content_sha256":"43ff4c526602d8dddab54830d864582c261a653b1a750a6216a3657b484065d7","schema_version":"1.0","event_id":"sha256:43ff4c526602d8dddab54830d864582c261a653b1a750a6216a3657b484065d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZHZ4P5XWMOHOAUL7PRTMTRZ65Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FAT: Federated Adversarial Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Ambrish Rawat, Beat Buesser, Giulio Zizzo, Mathieu Sinn","submitted_at":"2020-12-03T09:47:47Z","abstract_excerpt":"Federated learning (FL) is one of the most important paradigms addressing privacy and data governance issues in machine learning (ML). Adversarial training has emerged, so far, as the most promising approach against evasion threats on ML models. In this paper, we take the first known steps towards federated adversarial training (FAT) combining both methods to reduce the threat of evasion during inference while preserving the data privacy during training. We investigate the effectiveness of the FAT protocol for idealised federated settings using MNIST, Fashion-MNIST, and CIFAR10, and provide fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.01791","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/2012.01791/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":"2026-07-05T01:56:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xzP3b6boLddBEF50vnhb37vIlf2gu9y40jFc2InGmgaLPYnldJYpnOs1wyqCDZ3TwPWF/TLu3iPTcBHhR/KKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:51:55.230845Z"},"content_sha256":"23502aa1d13e8c715540c656aca9f9cbf3683533588d3f25e9afd747d384905f","schema_version":"1.0","event_id":"sha256:23502aa1d13e8c715540c656aca9f9cbf3683533588d3f25e9afd747d384905f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZHZ4P5XWMOHOAUL7PRTMTRZ65Z/bundle.json","state_url":"https://pith.science/pith/ZHZ4P5XWMOHOAUL7PRTMTRZ65Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZHZ4P5XWMOHOAUL7PRTMTRZ65Z/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":"2026-08-09T06:51:55Z","links":{"resolver":"https://pith.science/pith/ZHZ4P5XWMOHOAUL7PRTMTRZ65Z","bundle":"https://pith.science/pith/ZHZ4P5XWMOHOAUL7PRTMTRZ65Z/bundle.json","state":"https://pith.science/pith/ZHZ4P5XWMOHOAUL7PRTMTRZ65Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZHZ4P5XWMOHOAUL7PRTMTRZ65Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZHZ4P5XWMOHOAUL7PRTMTRZ65Z","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":"18401c770367c6d76d325af2cca5d9191637e5fa28da692d8bc6098d93a340ef","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-03T09:47:47Z","title_canon_sha256":"51c1bd1a62855ae597266b2c19f92af631c9f064298cd2bef43f1984a45d96a8"},"schema_version":"1.0","source":{"id":"2012.01791","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.01791","created_at":"2026-07-05T01:56:50Z"},{"alias_kind":"arxiv_version","alias_value":"2012.01791v1","created_at":"2026-07-05T01:56:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.01791","created_at":"2026-07-05T01:56:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZHZ4P5XWMOHO","created_at":"2026-07-05T01:56:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZHZ4P5XWMOHOAUL7","created_at":"2026-07-05T01:56:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZHZ4P5XW","created_at":"2026-07-05T01:56:50Z"}],"graph_snapshots":[{"event_id":"sha256:23502aa1d13e8c715540c656aca9f9cbf3683533588d3f25e9afd747d384905f","target":"graph","created_at":"2026-07-05T01:56:50Z","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/2012.01791/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated learning (FL) is one of the most important paradigms addressing privacy and data governance issues in machine learning (ML). Adversarial training has emerged, so far, as the most promising approach against evasion threats on ML models. In this paper, we take the first known steps towards federated adversarial training (FAT) combining both methods to reduce the threat of evasion during inference while preserving the data privacy during training. We investigate the effectiveness of the FAT protocol for idealised federated settings using MNIST, Fashion-MNIST, and CIFAR10, and provide fi","authors_text":"Ambrish Rawat, Beat Buesser, Giulio Zizzo, Mathieu Sinn","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-03T09:47:47Z","title":"FAT: Federated Adversarial Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.01791","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":"sha256:43ff4c526602d8dddab54830d864582c261a653b1a750a6216a3657b484065d7","target":"record","created_at":"2026-07-05T01:56:50Z","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":"18401c770367c6d76d325af2cca5d9191637e5fa28da692d8bc6098d93a340ef","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-03T09:47:47Z","title_canon_sha256":"51c1bd1a62855ae597266b2c19f92af631c9f064298cd2bef43f1984a45d96a8"},"schema_version":"1.0","source":{"id":"2012.01791","kind":"arxiv","version":1}},"canonical_sha256":"c9f3c7f6f6638ee0517f7c66c9c73eee4b6c0b78a56e15bf9b7f22ec2c3a0087","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9f3c7f6f6638ee0517f7c66c9c73eee4b6c0b78a56e15bf9b7f22ec2c3a0087","first_computed_at":"2026-07-05T01:56:50.200872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:50.200872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CtYi5LpMN4RHXdCzCE1UifYPmtjZEGu2xym9igrU2VNSfpu0VsgiQXqRvRyAsYuHhwD3COYLDU7+TVODwD6NAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:50.201221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.01791","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43ff4c526602d8dddab54830d864582c261a653b1a750a6216a3657b484065d7","sha256:23502aa1d13e8c715540c656aca9f9cbf3683533588d3f25e9afd747d384905f"],"state_sha256":"a058944e04a33700c6b4d72b2fb75c4ae4ba686edadf077b9f2e40047654dbfc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cuu8xirHucigotxWmc4nRvG62gOj7KMomPmzAad0GALOJMbMa4UpMAruPboY+sfeUJEJRhMKqD3T5wfb+wF5CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:51:55.235632Z","bundle_sha256":"84c6464e1522f07e017ca0c53dc7a3cd70ea41c14d0c7244c4bc614f7a28b739"}}