{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VKVQZESZVJXXX7UO2OD3TTNDIR","short_pith_number":"pith:VKVQZESZ","canonical_record":{"source":{"id":"1810.01279","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-01T05:23:15Z","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"title_canon_sha256":"ee0716d9cc643ded02c45358d5dfe984903d141d69ed8e1d7e7a8676f45b469d","abstract_canon_sha256":"fdc926c89a1a6beb502df4fef76e0917e25d7dcabad43b61534bc324e8060313"},"schema_version":"1.0"},"canonical_sha256":"aaab0c9259aa6f7bfe8ed387b9cda3446bbb7b2bd0daebb077df29b30020c1f4","source":{"kind":"arxiv","id":"1810.01279","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.01279","created_at":"2026-05-17T23:47:02Z"},{"alias_kind":"arxiv_version","alias_value":"1810.01279v2","created_at":"2026-05-17T23:47:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01279","created_at":"2026-05-17T23:47:02Z"},{"alias_kind":"pith_short_12","alias_value":"VKVQZESZVJXX","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VKVQZESZVJXXX7UO","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VKVQZESZ","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VKVQZESZVJXXX7UO2OD3TTNDIR","target":"record","payload":{"canonical_record":{"source":{"id":"1810.01279","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-01T05:23:15Z","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"title_canon_sha256":"ee0716d9cc643ded02c45358d5dfe984903d141d69ed8e1d7e7a8676f45b469d","abstract_canon_sha256":"fdc926c89a1a6beb502df4fef76e0917e25d7dcabad43b61534bc324e8060313"},"schema_version":"1.0"},"canonical_sha256":"aaab0c9259aa6f7bfe8ed387b9cda3446bbb7b2bd0daebb077df29b30020c1f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:02.740310Z","signature_b64":"ZEEI+9fO0jv7CMWta1tQA/LpJAjKdLo9FGCBWUNE5p/3i7h4C4AId9lDpXeTqza+7N649/2VbXjLHYSZCxe5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aaab0c9259aa6f7bfe8ed387b9cda3446bbb7b2bd0daebb077df29b30020c1f4","last_reissued_at":"2026-05-17T23:47:02.739791Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:02.739791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.01279","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ramLhP/vCNZ9SWJF3dRgHWUmu+sqotcrCvTC6zr0lYpsQ5hJK8APpl7e+CX4ZEjeUtvYN4BRBNoPatWXHLJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:51:41.592693Z"},"content_sha256":"091e7dcac7492e2592e34977c888eea4bcc013e3f551a50d18ff28f0966fd85b","schema_version":"1.0","event_id":"sha256:091e7dcac7492e2592e34977c888eea4bcc013e3f551a50d18ff28f0966fd85b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VKVQZESZVJXXX7UO2OD3TTNDIR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Chongruo Wu, Xuanqing Liu, Yao Li","submitted_at":"2018-10-01T05:23:15Z","abstract_excerpt":"We present a new algorithm to train a robust neural network against adversarial attacks. Our algorithm is motivated by the following two ideas. First, although recent work has demonstrated that fusing randomness can improve the robustness of neural networks (Liu 2017), we noticed that adding noise blindly to all the layers is not the optimal way to incorporate randomness. Instead, we model randomness under the framework of Bayesian Neural Network (BNN) to formally learn the posterior distribution of models in a scalable way. Second, we formulate the mini-max problem in BNN to learn the best mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01279","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:47:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lrkPDEgrKwWk8bhpeZOPsA4bvNXSnl9z4P/TuZ/LfEAqU09EZotIfqJaprQSY8SafEpoj3uPNgezTwmjSrkzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:51:41.593358Z"},"content_sha256":"8556412ebc25b8d272137db35be78305012109592d406a621d16731cc39fba50","schema_version":"1.0","event_id":"sha256:8556412ebc25b8d272137db35be78305012109592d406a621d16731cc39fba50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VKVQZESZVJXXX7UO2OD3TTNDIR/bundle.json","state_url":"https://pith.science/pith/VKVQZESZVJXXX7UO2OD3TTNDIR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VKVQZESZVJXXX7UO2OD3TTNDIR/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":"2026-05-25T16:51:41Z","links":{"resolver":"https://pith.science/pith/VKVQZESZVJXXX7UO2OD3TTNDIR","bundle":"https://pith.science/pith/VKVQZESZVJXXX7UO2OD3TTNDIR/bundle.json","state":"https://pith.science/pith/VKVQZESZVJXXX7UO2OD3TTNDIR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VKVQZESZVJXXX7UO2OD3TTNDIR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VKVQZESZVJXXX7UO2OD3TTNDIR","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":"fdc926c89a1a6beb502df4fef76e0917e25d7dcabad43b61534bc324e8060313","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-01T05:23:15Z","title_canon_sha256":"ee0716d9cc643ded02c45358d5dfe984903d141d69ed8e1d7e7a8676f45b469d"},"schema_version":"1.0","source":{"id":"1810.01279","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.01279","created_at":"2026-05-17T23:47:02Z"},{"alias_kind":"arxiv_version","alias_value":"1810.01279v2","created_at":"2026-05-17T23:47:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01279","created_at":"2026-05-17T23:47:02Z"},{"alias_kind":"pith_short_12","alias_value":"VKVQZESZVJXX","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VKVQZESZVJXXX7UO","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VKVQZESZ","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:8556412ebc25b8d272137db35be78305012109592d406a621d16731cc39fba50","target":"graph","created_at":"2026-05-17T23:47:02Z","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"},"paper":{"abstract_excerpt":"We present a new algorithm to train a robust neural network against adversarial attacks. Our algorithm is motivated by the following two ideas. First, although recent work has demonstrated that fusing randomness can improve the robustness of neural networks (Liu 2017), we noticed that adding noise blindly to all the layers is not the optimal way to incorporate randomness. Instead, we model randomness under the framework of Bayesian Neural Network (BNN) to formally learn the posterior distribution of models in a scalable way. Second, we formulate the mini-max problem in BNN to learn the best mo","authors_text":"Cho-Jui Hsieh, Chongruo Wu, Xuanqing Liu, Yao Li","cross_cats":["cs.AI","cs.CR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-01T05:23:15Z","title":"Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01279","kind":"arxiv","version":2},"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":"sha256:091e7dcac7492e2592e34977c888eea4bcc013e3f551a50d18ff28f0966fd85b","target":"record","created_at":"2026-05-17T23:47:02Z","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":"fdc926c89a1a6beb502df4fef76e0917e25d7dcabad43b61534bc324e8060313","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-01T05:23:15Z","title_canon_sha256":"ee0716d9cc643ded02c45358d5dfe984903d141d69ed8e1d7e7a8676f45b469d"},"schema_version":"1.0","source":{"id":"1810.01279","kind":"arxiv","version":2}},"canonical_sha256":"aaab0c9259aa6f7bfe8ed387b9cda3446bbb7b2bd0daebb077df29b30020c1f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aaab0c9259aa6f7bfe8ed387b9cda3446bbb7b2bd0daebb077df29b30020c1f4","first_computed_at":"2026-05-17T23:47:02.739791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:02.739791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZEEI+9fO0jv7CMWta1tQA/LpJAjKdLo9FGCBWUNE5p/3i7h4C4AId9lDpXeTqza+7N649/2VbXjLHYSZCxe5DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:02.740310Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.01279","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:091e7dcac7492e2592e34977c888eea4bcc013e3f551a50d18ff28f0966fd85b","sha256:8556412ebc25b8d272137db35be78305012109592d406a621d16731cc39fba50"],"state_sha256":"be371fafe596399bcb9629d5ef6b7c3a43437e01ab7605dcf90f4fa9fd6f5e56"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3DdyszRDZBf28cJ2S5Q5mv4olne3vBNhCGpYV6+SVplkjmT+nLMGtKkWaSy8sXQdcqclcIXqn5nAvelgMaYGAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:51:41.596811Z","bundle_sha256":"e249fca834fa394aeda0f8de3d0f22802687817d0a3365fce7f61a8c041e8c49"}}