{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:R3LYH3MVAR3LQQSOCTQWKI6GJ2","short_pith_number":"pith:R3LYH3MV","canonical_record":{"source":{"id":"2406.03117","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T10:10:03Z","cross_cats_sorted":[],"title_canon_sha256":"bad6f1ddd473d20e6a49270165612b5059e085d26298ea94ca634e127037e84e","abstract_canon_sha256":"bc4db1f572fbbbb13786ecc38a46499873939b78fc6c5424986ee4910abf3762"},"schema_version":"1.0"},"canonical_sha256":"8ed783ed950476b8424e14e16523c64eb19db23a76072a6355182eb5fc7d5057","source":{"kind":"arxiv","id":"2406.03117","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03117","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03117v1","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03117","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"pith_short_12","alias_value":"R3LYH3MVAR3L","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"pith_short_16","alias_value":"R3LYH3MVAR3LQQSO","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"pith_short_8","alias_value":"R3LYH3MV","created_at":"2026-07-05T08:27:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:R3LYH3MVAR3LQQSOCTQWKI6GJ2","target":"record","payload":{"canonical_record":{"source":{"id":"2406.03117","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T10:10:03Z","cross_cats_sorted":[],"title_canon_sha256":"bad6f1ddd473d20e6a49270165612b5059e085d26298ea94ca634e127037e84e","abstract_canon_sha256":"bc4db1f572fbbbb13786ecc38a46499873939b78fc6c5424986ee4910abf3762"},"schema_version":"1.0"},"canonical_sha256":"8ed783ed950476b8424e14e16523c64eb19db23a76072a6355182eb5fc7d5057","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:51.572290Z","signature_b64":"xfgqkaXAHcXXZ5AyrHyVllIJGn6CGkkMYHggB6sL7U5c0lIoplxn0Zuk24RfwBX9JBWAJoGqagDHPbWER4ERBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ed783ed950476b8424e14e16523c64eb19db23a76072a6355182eb5fc7d5057","last_reissued_at":"2026-07-05T08:27:51.571872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:51.571872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.03117","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":"2026-07-05T08:27:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O1vIafkES0gpVdlGTp+MgI57CSr2+QffTxUGwG3BQ0dh6EhEfum8hHz5i2QSeN64BU0TZhfDT4Z9iRyJjsBTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:21:35.123797Z"},"content_sha256":"22d7f46be95026b56fb9880fae1c698091236ff54d810e7820ce7b71e9402efe","schema_version":"1.0","event_id":"sha256:22d7f46be95026b56fb9880fae1c698091236ff54d810e7820ce7b71e9402efe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:R3LYH3MVAR3LQQSOCTQWKI6GJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mukesh Singhal, Zhixun He","submitted_at":"2024-06-05T10:10:03Z","abstract_excerpt":"Deep Neural Networks (DNN) have become a promising paradigm when developing Artificial Intelligence (AI) and Machine Learning (ML) applications. However, DNN applications are vulnerable to fake data that are crafted with adversarial attack algorithms. Under adversarial attacks, the prediction accuracy of DNN applications suffers, making them unreliable. In order to defend against adversarial attacks, we introduce a novel noise-reduction procedure, Vector Quantization U-Net (VQUNet), to reduce adversarial noise and reconstruct data with high fidelity. VQUNet features a discrete latent represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03117","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/2406.03117/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":"2026-07-05T08:27:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GRqDDD0XS5Bb+twEjzPwcgiose6WqqEnHUwN/cr0kHEabqrYvUehoQRhwSgrx06bkpaEkznBgTT0SNPBLXcYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:21:35.124614Z"},"content_sha256":"c10badd624d3b6607ed9f03af21388faa13915b2a8d0caac819d3e9438cc47ba","schema_version":"1.0","event_id":"sha256:c10badd624d3b6607ed9f03af21388faa13915b2a8d0caac819d3e9438cc47ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R3LYH3MVAR3LQQSOCTQWKI6GJ2/bundle.json","state_url":"https://pith.science/pith/R3LYH3MVAR3LQQSOCTQWKI6GJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R3LYH3MVAR3LQQSOCTQWKI6GJ2/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":"2026-08-07T05:21:35Z","links":{"resolver":"https://pith.science/pith/R3LYH3MVAR3LQQSOCTQWKI6GJ2","bundle":"https://pith.science/pith/R3LYH3MVAR3LQQSOCTQWKI6GJ2/bundle.json","state":"https://pith.science/pith/R3LYH3MVAR3LQQSOCTQWKI6GJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R3LYH3MVAR3LQQSOCTQWKI6GJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R3LYH3MVAR3LQQSOCTQWKI6GJ2","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":"bc4db1f572fbbbb13786ecc38a46499873939b78fc6c5424986ee4910abf3762","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T10:10:03Z","title_canon_sha256":"bad6f1ddd473d20e6a49270165612b5059e085d26298ea94ca634e127037e84e"},"schema_version":"1.0","source":{"id":"2406.03117","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.03117","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"arxiv_version","alias_value":"2406.03117v1","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03117","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"pith_short_12","alias_value":"R3LYH3MVAR3L","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"pith_short_16","alias_value":"R3LYH3MVAR3LQQSO","created_at":"2026-07-05T08:27:51Z"},{"alias_kind":"pith_short_8","alias_value":"R3LYH3MV","created_at":"2026-07-05T08:27:51Z"}],"graph_snapshots":[{"event_id":"sha256:c10badd624d3b6607ed9f03af21388faa13915b2a8d0caac819d3e9438cc47ba","target":"graph","created_at":"2026-07-05T08:27:51Z","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/2406.03117/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Neural Networks (DNN) have become a promising paradigm when developing Artificial Intelligence (AI) and Machine Learning (ML) applications. However, DNN applications are vulnerable to fake data that are crafted with adversarial attack algorithms. Under adversarial attacks, the prediction accuracy of DNN applications suffers, making them unreliable. In order to defend against adversarial attacks, we introduce a novel noise-reduction procedure, Vector Quantization U-Net (VQUNet), to reduce adversarial noise and reconstruct data with high fidelity. VQUNet features a discrete latent represent","authors_text":"Mukesh Singhal, Zhixun He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T10:10:03Z","title":"VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03117","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":"sha256:22d7f46be95026b56fb9880fae1c698091236ff54d810e7820ce7b71e9402efe","target":"record","created_at":"2026-07-05T08:27:51Z","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":"bc4db1f572fbbbb13786ecc38a46499873939b78fc6c5424986ee4910abf3762","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T10:10:03Z","title_canon_sha256":"bad6f1ddd473d20e6a49270165612b5059e085d26298ea94ca634e127037e84e"},"schema_version":"1.0","source":{"id":"2406.03117","kind":"arxiv","version":1}},"canonical_sha256":"8ed783ed950476b8424e14e16523c64eb19db23a76072a6355182eb5fc7d5057","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ed783ed950476b8424e14e16523c64eb19db23a76072a6355182eb5fc7d5057","first_computed_at":"2026-07-05T08:27:51.571872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:51.571872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xfgqkaXAHcXXZ5AyrHyVllIJGn6CGkkMYHggB6sL7U5c0lIoplxn0Zuk24RfwBX9JBWAJoGqagDHPbWER4ERBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:51.572290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.03117","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22d7f46be95026b56fb9880fae1c698091236ff54d810e7820ce7b71e9402efe","sha256:c10badd624d3b6607ed9f03af21388faa13915b2a8d0caac819d3e9438cc47ba"],"state_sha256":"b849b5d4e17ed6660a5d1b39d4e9648fc7676673ced94bf4bae44b96bb86bbf4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F6zP6foyr3uYDIM/fgOmjr2sEDyJXnJPJseA2Y/bpUvl/LfxupvX/+Aoaza2nhhtif5/7c2PlBdZ+PHCMPzZAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:21:35.131517Z","bundle_sha256":"bf52d98b9e8622b4ed9a356a166d4e0a55ba960abe334efdbff9eb04a9d55123"}}