{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3O7EVIMNP6IDJICIP7FPFIYKTF","short_pith_number":"pith:3O7EVIMN","canonical_record":{"source":{"id":"2101.01543","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-05T14:31:53Z","cross_cats_sorted":[],"title_canon_sha256":"f382eb2e96d5b98a2ee73d78048ff171b633008ed7fe852988e8af2665a23340","abstract_canon_sha256":"37b47f273bd60f77b22f96ae764f24b81428616e594b9cab4b514debcb024974"},"schema_version":"1.0"},"canonical_sha256":"dbbe4aa18d7f9034a0487fcaf2a30a997b658771ee7fb1dbc90927f4b23e4c9e","source":{"kind":"arxiv","id":"2101.01543","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.01543","created_at":"2026-07-05T02:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"2101.01543v2","created_at":"2026-07-05T02:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01543","created_at":"2026-07-05T02:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"3O7EVIMNP6ID","created_at":"2026-07-05T02:54:53Z"},{"alias_kind":"pith_short_16","alias_value":"3O7EVIMNP6IDJICI","created_at":"2026-07-05T02:54:53Z"},{"alias_kind":"pith_short_8","alias_value":"3O7EVIMN","created_at":"2026-07-05T02:54:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3O7EVIMNP6IDJICIP7FPFIYKTF","target":"record","payload":{"canonical_record":{"source":{"id":"2101.01543","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-05T14:31:53Z","cross_cats_sorted":[],"title_canon_sha256":"f382eb2e96d5b98a2ee73d78048ff171b633008ed7fe852988e8af2665a23340","abstract_canon_sha256":"37b47f273bd60f77b22f96ae764f24b81428616e594b9cab4b514debcb024974"},"schema_version":"1.0"},"canonical_sha256":"dbbe4aa18d7f9034a0487fcaf2a30a997b658771ee7fb1dbc90927f4b23e4c9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:53.085416Z","signature_b64":"ChY0eQI6PCmXh0eF+zkBvdkRxTnGFtHTnkLx1dABVXnkWogMwcD6XF0bVMjriUFjrLh3xHm63cHsOa5HRZ/TCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbbe4aa18d7f9034a0487fcaf2a30a997b658771ee7fb1dbc90927f4b23e4c9e","last_reissued_at":"2026-07-05T02:54:53.084932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:53.084932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.01543","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":"2026-07-05T02:54:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jDe9vLsDKhF5BY4IKca4bYjMcSGPKdWn5ym5f7/YGbBuzJphAf0q7prd0JxPAsrzKkKKOyMpMH51oqU29eB8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:10:08.346354Z"},"content_sha256":"4d1ea621d53420fc87a2068b9ac35252811aa55912f7af2b4824fc81d0b015c0","schema_version":"1.0","event_id":"sha256:4d1ea621d53420fc87a2068b9ac35252811aa55912f7af2b4824fc81d0b015c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3O7EVIMNP6IDJICIP7FPFIYKTF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Moitra, Priyadarshini Panda, Rachel Sterneck","submitted_at":"2021-01-05T14:31:53Z","abstract_excerpt":"Neural networks have achieved remarkable performance in computer vision, however they are vulnerable to adversarial examples. Adversarial examples are inputs that have been carefully perturbed to fool classifier networks, while appearing unchanged to humans. Based on prior works on detecting adversaries, we propose a structured methodology of augmenting a deep neural network (DNN) with a detector subnetwork. We use $\\textit{Adversarial Noise Sensitivity}$ (ANS), a novel metric for measuring the adversarial gradient contribution of different intermediate layers of a network. Based on the ANS va"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01543","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2101.01543/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":"2026-07-05T02:54:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yQ6lleaUg8melQlNsQUrkRwFVEGWTv3GdYXQcj2rdL+801aE3wn41Mj7b5IMSqFLFUZIYaD4maV3TnspM+V5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:10:08.346855Z"},"content_sha256":"d270c2f2ce6b1f596c76c5ae18453af319068f7d0300eda540ce918d01037f7e","schema_version":"1.0","event_id":"sha256:d270c2f2ce6b1f596c76c5ae18453af319068f7d0300eda540ce918d01037f7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3O7EVIMNP6IDJICIP7FPFIYKTF/bundle.json","state_url":"https://pith.science/pith/3O7EVIMNP6IDJICIP7FPFIYKTF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3O7EVIMNP6IDJICIP7FPFIYKTF/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":"2026-08-21T22:10:08Z","links":{"resolver":"https://pith.science/pith/3O7EVIMNP6IDJICIP7FPFIYKTF","bundle":"https://pith.science/pith/3O7EVIMNP6IDJICIP7FPFIYKTF/bundle.json","state":"https://pith.science/pith/3O7EVIMNP6IDJICIP7FPFIYKTF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3O7EVIMNP6IDJICIP7FPFIYKTF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3O7EVIMNP6IDJICIP7FPFIYKTF","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":"37b47f273bd60f77b22f96ae764f24b81428616e594b9cab4b514debcb024974","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-05T14:31:53Z","title_canon_sha256":"f382eb2e96d5b98a2ee73d78048ff171b633008ed7fe852988e8af2665a23340"},"schema_version":"1.0","source":{"id":"2101.01543","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.01543","created_at":"2026-07-05T02:54:53Z"},{"alias_kind":"arxiv_version","alias_value":"2101.01543v2","created_at":"2026-07-05T02:54:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.01543","created_at":"2026-07-05T02:54:53Z"},{"alias_kind":"pith_short_12","alias_value":"3O7EVIMNP6ID","created_at":"2026-07-05T02:54:53Z"},{"alias_kind":"pith_short_16","alias_value":"3O7EVIMNP6IDJICI","created_at":"2026-07-05T02:54:53Z"},{"alias_kind":"pith_short_8","alias_value":"3O7EVIMN","created_at":"2026-07-05T02:54:53Z"}],"graph_snapshots":[{"event_id":"sha256:d270c2f2ce6b1f596c76c5ae18453af319068f7d0300eda540ce918d01037f7e","target":"graph","created_at":"2026-07-05T02:54:53Z","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/2101.01543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural networks have achieved remarkable performance in computer vision, however they are vulnerable to adversarial examples. Adversarial examples are inputs that have been carefully perturbed to fool classifier networks, while appearing unchanged to humans. Based on prior works on detecting adversaries, we propose a structured methodology of augmenting a deep neural network (DNN) with a detector subnetwork. We use $\\textit{Adversarial Noise Sensitivity}$ (ANS), a novel metric for measuring the adversarial gradient contribution of different intermediate layers of a network. Based on the ANS va","authors_text":"Abhishek Moitra, Priyadarshini Panda, Rachel Sterneck","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-05T14:31:53Z","title":"Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.01543","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":"sha256:4d1ea621d53420fc87a2068b9ac35252811aa55912f7af2b4824fc81d0b015c0","target":"record","created_at":"2026-07-05T02:54:53Z","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":"37b47f273bd60f77b22f96ae764f24b81428616e594b9cab4b514debcb024974","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-05T14:31:53Z","title_canon_sha256":"f382eb2e96d5b98a2ee73d78048ff171b633008ed7fe852988e8af2665a23340"},"schema_version":"1.0","source":{"id":"2101.01543","kind":"arxiv","version":2}},"canonical_sha256":"dbbe4aa18d7f9034a0487fcaf2a30a997b658771ee7fb1dbc90927f4b23e4c9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbbe4aa18d7f9034a0487fcaf2a30a997b658771ee7fb1dbc90927f4b23e4c9e","first_computed_at":"2026-07-05T02:54:53.084932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:54:53.084932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ChY0eQI6PCmXh0eF+zkBvdkRxTnGFtHTnkLx1dABVXnkWogMwcD6XF0bVMjriUFjrLh3xHm63cHsOa5HRZ/TCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:54:53.085416Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.01543","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d1ea621d53420fc87a2068b9ac35252811aa55912f7af2b4824fc81d0b015c0","sha256:d270c2f2ce6b1f596c76c5ae18453af319068f7d0300eda540ce918d01037f7e"],"state_sha256":"86c6fd76a104c7e80cf1cdf8e8bb0201dbea1f801e3a47d16b0aadaaaebbb885"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YV9DNJq0z7JTSCujzRmOfk5qEhibjq9a6cSGEWWq0CXJhVv9Vjdrz+zI1LrAjYq9gli6ZUELZcTmILXd74zXCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T22:10:08.351886Z","bundle_sha256":"7b40c3d96532c8e54fff6f998360380c3a4d342da0dcfe5132785c50a4d02f51"}}