{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:FG3NBK65X7YENSUXOC35XXA2CX","short_pith_number":"pith:FG3NBK65","canonical_record":{"source":{"id":"1812.07385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T21:48:46Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"055e7907f408894a4db94d67b15f1f3ff33e1753ab90c5285c921032e55dc199","abstract_canon_sha256":"0730279d3df09586f08c00e84ac8f74a9f2b6d461fc34414b6a383da5008f4e9"},"schema_version":"1.0"},"canonical_sha256":"29b6d0abddbff046ca9770b7dbdc1a15f6c8237119d80b6a591820e05b8acafa","source":{"kind":"arxiv","id":"1812.07385","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07385","created_at":"2026-05-17T23:58:00Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07385v1","created_at":"2026-05-17T23:58:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07385","created_at":"2026-05-17T23:58:00Z"},{"alias_kind":"pith_short_12","alias_value":"FG3NBK65X7YE","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FG3NBK65X7YENSUX","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FG3NBK65","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:FG3NBK65X7YENSUXOC35XXA2CX","target":"record","payload":{"canonical_record":{"source":{"id":"1812.07385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T21:48:46Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"055e7907f408894a4db94d67b15f1f3ff33e1753ab90c5285c921032e55dc199","abstract_canon_sha256":"0730279d3df09586f08c00e84ac8f74a9f2b6d461fc34414b6a383da5008f4e9"},"schema_version":"1.0"},"canonical_sha256":"29b6d0abddbff046ca9770b7dbdc1a15f6c8237119d80b6a591820e05b8acafa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:00.665167Z","signature_b64":"xFxk38JM0yzRR5P7SpilIYqRquktI/A2N19yh3m2JjznHSl5KOEqsIk7n+L1mFKxZtuS5Sk+Qxav0RvAc4XgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29b6d0abddbff046ca9770b7dbdc1a15f6c8237119d80b6a591820e05b8acafa","last_reissued_at":"2026-05-17T23:58:00.664557Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:00.664557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.07385","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":"2026-05-17T23:58:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OJGkcqoIAvrdfy1PsYRj/Xbp48XgACURmP0wihhuv+L/n14eqnOPJJBP5HZWlkEvWJ+8ExjKntRGDuOfG63GCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:41:01.947299Z"},"content_sha256":"a168cbc0170666784d7de1d20476b8e86dedf975218af7f725e9fb79490a5693","schema_version":"1.0","event_id":"sha256:a168cbc0170666784d7de1d20476b8e86dedf975218af7f725e9fb79490a5693"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:FG3NBK65X7YENSUXOC35XXA2CX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Perturbation Analysis of Learning Algorithms: A Unifying Perspective on Generation of Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arash Behboodi, Emilio Rafael Balda, Rudolf Mathar","submitted_at":"2018-12-15T21:48:46Z","abstract_excerpt":"Despite the tremendous success of deep neural networks in various learning problems, it has been observed that adding an intentionally designed adversarial perturbation to inputs of these architectures leads to erroneous classification with high confidence in the prediction. In this work, we propose a general framework based on the perturbation analysis of learning algorithms which consists of convex programming and is able to recover many current adversarial attacks as special cases. The framework can be used to propose novel attacks against learning algorithms for classification and regressi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07385","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":""},"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":"2026-05-17T23:58:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+blvmc3M74AieAE6f0ieYc/8tHPpIU4nWMvYPQgCxCV35N4Ng6ypfwlk++9lRK9Wgm0WOKHpF/XoJ680CQUUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:41:01.948047Z"},"content_sha256":"07a33821954a908148bfc72f77c570faf711bc774b4baa711aecd6731a129778","schema_version":"1.0","event_id":"sha256:07a33821954a908148bfc72f77c570faf711bc774b4baa711aecd6731a129778"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FG3NBK65X7YENSUXOC35XXA2CX/bundle.json","state_url":"https://pith.science/pith/FG3NBK65X7YENSUXOC35XXA2CX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FG3NBK65X7YENSUXOC35XXA2CX/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":"2026-06-09T08:41:01Z","links":{"resolver":"https://pith.science/pith/FG3NBK65X7YENSUXOC35XXA2CX","bundle":"https://pith.science/pith/FG3NBK65X7YENSUXOC35XXA2CX/bundle.json","state":"https://pith.science/pith/FG3NBK65X7YENSUXOC35XXA2CX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FG3NBK65X7YENSUXOC35XXA2CX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:FG3NBK65X7YENSUXOC35XXA2CX","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":"0730279d3df09586f08c00e84ac8f74a9f2b6d461fc34414b6a383da5008f4e9","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T21:48:46Z","title_canon_sha256":"055e7907f408894a4db94d67b15f1f3ff33e1753ab90c5285c921032e55dc199"},"schema_version":"1.0","source":{"id":"1812.07385","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07385","created_at":"2026-05-17T23:58:00Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07385v1","created_at":"2026-05-17T23:58:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07385","created_at":"2026-05-17T23:58:00Z"},{"alias_kind":"pith_short_12","alias_value":"FG3NBK65X7YE","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"FG3NBK65X7YENSUX","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"FG3NBK65","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:07a33821954a908148bfc72f77c570faf711bc774b4baa711aecd6731a129778","target":"graph","created_at":"2026-05-17T23:58:00Z","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":"Despite the tremendous success of deep neural networks in various learning problems, it has been observed that adding an intentionally designed adversarial perturbation to inputs of these architectures leads to erroneous classification with high confidence in the prediction. In this work, we propose a general framework based on the perturbation analysis of learning algorithms which consists of convex programming and is able to recover many current adversarial attacks as special cases. The framework can be used to propose novel attacks against learning algorithms for classification and regressi","authors_text":"Arash Behboodi, Emilio Rafael Balda, Rudolf Mathar","cross_cats":["cs.AI","cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T21:48:46Z","title":"Perturbation Analysis of Learning Algorithms: A Unifying Perspective on Generation of Adversarial Examples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07385","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:a168cbc0170666784d7de1d20476b8e86dedf975218af7f725e9fb79490a5693","target":"record","created_at":"2026-05-17T23:58:00Z","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":"0730279d3df09586f08c00e84ac8f74a9f2b6d461fc34414b6a383da5008f4e9","cross_cats_sorted":["cs.AI","cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-15T21:48:46Z","title_canon_sha256":"055e7907f408894a4db94d67b15f1f3ff33e1753ab90c5285c921032e55dc199"},"schema_version":"1.0","source":{"id":"1812.07385","kind":"arxiv","version":1}},"canonical_sha256":"29b6d0abddbff046ca9770b7dbdc1a15f6c8237119d80b6a591820e05b8acafa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29b6d0abddbff046ca9770b7dbdc1a15f6c8237119d80b6a591820e05b8acafa","first_computed_at":"2026-05-17T23:58:00.664557Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:00.664557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xFxk38JM0yzRR5P7SpilIYqRquktI/A2N19yh3m2JjznHSl5KOEqsIk7n+L1mFKxZtuS5Sk+Qxav0RvAc4XgAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:00.665167Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.07385","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a168cbc0170666784d7de1d20476b8e86dedf975218af7f725e9fb79490a5693","sha256:07a33821954a908148bfc72f77c570faf711bc774b4baa711aecd6731a129778"],"state_sha256":"45a4147ba34f81dd1377a7594bab495d57d1b24c34657c9151ea82ac8d9ebf67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qtp/l22m4SmP52uOm4uji6d1kgmxtYQSTVDDPhOQSVCOw7NwTz8JIHguBCxGnfdSSHfxicPp2v1/Bt98Jb4mBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T08:41:01.952108Z","bundle_sha256":"d48434eae8f8dd6dd1cab6ea5197b38fcc89d22881f48dcaf0dd1f1ed473f8a9"}}