{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4EBNUVTUWEFB6LX4UKFV2AVEON","short_pith_number":"pith:4EBNUVTU","canonical_record":{"source":{"id":"2408.13102","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-23T14:25:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b50826712562699bb429baf8eb7fca3e74654506a9527d960c11aee927b86f2b","abstract_canon_sha256":"d4e6f699f8ab6198b207102431583bc3c90b55ebd9518b0a2374b310e7a8dc43"},"schema_version":"1.0"},"canonical_sha256":"e102da5674b10a1f2efca28b5d02a47347f7b343f4dc669748461a4cbe5caa0c","source":{"kind":"arxiv","id":"2408.13102","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13102","created_at":"2026-07-05T08:58:35Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13102v1","created_at":"2026-07-05T08:58:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13102","created_at":"2026-07-05T08:58:35Z"},{"alias_kind":"pith_short_12","alias_value":"4EBNUVTUWEFB","created_at":"2026-07-05T08:58:35Z"},{"alias_kind":"pith_short_16","alias_value":"4EBNUVTUWEFB6LX4","created_at":"2026-07-05T08:58:35Z"},{"alias_kind":"pith_short_8","alias_value":"4EBNUVTU","created_at":"2026-07-05T08:58:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4EBNUVTUWEFB6LX4UKFV2AVEON","target":"record","payload":{"canonical_record":{"source":{"id":"2408.13102","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-23T14:25:12Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b50826712562699bb429baf8eb7fca3e74654506a9527d960c11aee927b86f2b","abstract_canon_sha256":"d4e6f699f8ab6198b207102431583bc3c90b55ebd9518b0a2374b310e7a8dc43"},"schema_version":"1.0"},"canonical_sha256":"e102da5674b10a1f2efca28b5d02a47347f7b343f4dc669748461a4cbe5caa0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:35.515036Z","signature_b64":"12nrsINCMhx5csyGDRJOzysSpd2As39hY2ynEVx9L0WUokoKxwZpNg/cTUYdGFvlcnP05VxBIYVMTBmauGybBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e102da5674b10a1f2efca28b5d02a47347f7b343f4dc669748461a4cbe5caa0c","last_reissued_at":"2026-07-05T08:58:35.514578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:35.514578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.13102","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":"2026-07-05T08:58:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BG+67qmOtUsZ8saia6io2wDr/jry3n3q2/CGZWuE71prn0lzJYttufDLtngGA3pyf0ScmmvqtVl0AlTBvFwbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:31:30.985091Z"},"content_sha256":"a25f418878530e18a92b586bd6f1729d58cb505bf2b74e11bdd4f0c1b42983dc","schema_version":"1.0","event_id":"sha256:a25f418878530e18a92b586bd6f1729d58cb505bf2b74e11bdd4f0c1b42983dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4EBNUVTUWEFB6LX4UKFV2AVEON","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Guiseppe Nicosia, Haoran Duan, Huizhi Liang, Rajiv Ranjan, Vaclav Snasel, Varun Ojha, Yang Long, Zhenyu Liu","submitted_at":"2024-08-23T14:25:12Z","abstract_excerpt":"Adversarial training is one of the most effective methods for enhancing model robustness. Recent approaches incorporate adversarial distillation in adversarial training architectures. However, we notice two scenarios of defense methods that limit their performance: (1) Previous methods primarily use static ground truth for adversarial training, but this often causes robust overfitting; (2) The loss functions are either Mean Squared Error or KL-divergence leading to a sub-optimal performance on clean accuracy. To solve those problems, we propose a dynamic label adversarial training (DYNAT) algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13102","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/2408.13102/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":"2026-07-05T08:58:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OGXlbGeKokgZ/iB1j1clSNSBN1Hoh8vwWCvuBWyQhXxF4xq4Rh95XIVFpqXRgiLtFwy9xXfyrfRHYbWCLWF6DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:31:30.985475Z"},"content_sha256":"c3182890d3e12133a0fac076c32176b640dab7021002216f6fd73d509db7e934","schema_version":"1.0","event_id":"sha256:c3182890d3e12133a0fac076c32176b640dab7021002216f6fd73d509db7e934"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4EBNUVTUWEFB6LX4UKFV2AVEON/bundle.json","state_url":"https://pith.science/pith/4EBNUVTUWEFB6LX4UKFV2AVEON/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4EBNUVTUWEFB6LX4UKFV2AVEON/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":"2026-08-20T06:31:30Z","links":{"resolver":"https://pith.science/pith/4EBNUVTUWEFB6LX4UKFV2AVEON","bundle":"https://pith.science/pith/4EBNUVTUWEFB6LX4UKFV2AVEON/bundle.json","state":"https://pith.science/pith/4EBNUVTUWEFB6LX4UKFV2AVEON/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4EBNUVTUWEFB6LX4UKFV2AVEON/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4EBNUVTUWEFB6LX4UKFV2AVEON","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":"d4e6f699f8ab6198b207102431583bc3c90b55ebd9518b0a2374b310e7a8dc43","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-23T14:25:12Z","title_canon_sha256":"b50826712562699bb429baf8eb7fca3e74654506a9527d960c11aee927b86f2b"},"schema_version":"1.0","source":{"id":"2408.13102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13102","created_at":"2026-07-05T08:58:35Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13102v1","created_at":"2026-07-05T08:58:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13102","created_at":"2026-07-05T08:58:35Z"},{"alias_kind":"pith_short_12","alias_value":"4EBNUVTUWEFB","created_at":"2026-07-05T08:58:35Z"},{"alias_kind":"pith_short_16","alias_value":"4EBNUVTUWEFB6LX4","created_at":"2026-07-05T08:58:35Z"},{"alias_kind":"pith_short_8","alias_value":"4EBNUVTU","created_at":"2026-07-05T08:58:35Z"}],"graph_snapshots":[{"event_id":"sha256:c3182890d3e12133a0fac076c32176b640dab7021002216f6fd73d509db7e934","target":"graph","created_at":"2026-07-05T08:58:35Z","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/2408.13102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial training is one of the most effective methods for enhancing model robustness. Recent approaches incorporate adversarial distillation in adversarial training architectures. However, we notice two scenarios of defense methods that limit their performance: (1) Previous methods primarily use static ground truth for adversarial training, but this often causes robust overfitting; (2) The loss functions are either Mean Squared Error or KL-divergence leading to a sub-optimal performance on clean accuracy. To solve those problems, we propose a dynamic label adversarial training (DYNAT) algo","authors_text":"Guiseppe Nicosia, Haoran Duan, Huizhi Liang, Rajiv Ranjan, Vaclav Snasel, Varun Ojha, Yang Long, Zhenyu Liu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-23T14:25:12Z","title":"Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13102","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:a25f418878530e18a92b586bd6f1729d58cb505bf2b74e11bdd4f0c1b42983dc","target":"record","created_at":"2026-07-05T08:58:35Z","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":"d4e6f699f8ab6198b207102431583bc3c90b55ebd9518b0a2374b310e7a8dc43","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-23T14:25:12Z","title_canon_sha256":"b50826712562699bb429baf8eb7fca3e74654506a9527d960c11aee927b86f2b"},"schema_version":"1.0","source":{"id":"2408.13102","kind":"arxiv","version":1}},"canonical_sha256":"e102da5674b10a1f2efca28b5d02a47347f7b343f4dc669748461a4cbe5caa0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e102da5674b10a1f2efca28b5d02a47347f7b343f4dc669748461a4cbe5caa0c","first_computed_at":"2026-07-05T08:58:35.514578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:58:35.514578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"12nrsINCMhx5csyGDRJOzysSpd2As39hY2ynEVx9L0WUokoKxwZpNg/cTUYdGFvlcnP05VxBIYVMTBmauGybBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:58:35.515036Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.13102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a25f418878530e18a92b586bd6f1729d58cb505bf2b74e11bdd4f0c1b42983dc","sha256:c3182890d3e12133a0fac076c32176b640dab7021002216f6fd73d509db7e934"],"state_sha256":"4d7a496f453821a975945a0fb499beaa5487ba062fe94167946df94d4e436c90"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qqgoj1f/RnpCGPZtp1ppw1ux9LJn1ULGsnIOzV48vv1z9q/O8mAttCcrgHO2IgvuBl6sNyXVnxKdtdaeMtfEBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T06:31:30.988054Z","bundle_sha256":"73bacbcc87adc1732540e43ca042cf561b463b7ea6fc02bb60f672fda3e0a0b0"}}