{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:IISDFV3SI2AXUZHEGY4NQBZHMK","short_pith_number":"pith:IISDFV3S","canonical_record":{"source":{"id":"1511.07528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2015-11-24T01:07:08Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"499e81f45f7558040864f75e20168234642fd51d17f9d5d216600cc6a048405a","abstract_canon_sha256":"ab5790796d3bf532e4641e84f743ac9bf735fcb8e18602859b18c54c584f19e5"},"schema_version":"1.0"},"canonical_sha256":"422432d77246817a64e43638d8072762b9dc7b73684c7db70c416cbbe578a90f","source":{"kind":"arxiv","id":"1511.07528","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.07528","created_at":"2026-05-18T01:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"1511.07528v1","created_at":"2026-05-18T01:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07528","created_at":"2026-05-18T01:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"IISDFV3SI2AX","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"IISDFV3SI2AXUZHE","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"IISDFV3S","created_at":"2026-05-18T12:29:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:IISDFV3SI2AXUZHEGY4NQBZHMK","target":"record","payload":{"canonical_record":{"source":{"id":"1511.07528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2015-11-24T01:07:08Z","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"title_canon_sha256":"499e81f45f7558040864f75e20168234642fd51d17f9d5d216600cc6a048405a","abstract_canon_sha256":"ab5790796d3bf532e4641e84f743ac9bf735fcb8e18602859b18c54c584f19e5"},"schema_version":"1.0"},"canonical_sha256":"422432d77246817a64e43638d8072762b9dc7b73684c7db70c416cbbe578a90f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:04.541555Z","signature_b64":"YLl62KhZXawr7la6JWcEAKv8u9tJU7eBYr5bwIFJxaTAUr47GDkRGHvbvOrVOZIaLT4P5XH9owV98xuno1lPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"422432d77246817a64e43638d8072762b9dc7b73684c7db70c416cbbe578a90f","last_reissued_at":"2026-05-18T01:26:04.540994Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:04.540994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.07528","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":"2026-05-18T01:26:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TPD7Kd2+rGsiRxDqLKA0KHX7YgFNR+OQH7RUKpLDkbft0jX/vmajlw/eZYylEP2BcTm4iMILJKgzcGUc91kNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T03:21:29.581120Z"},"content_sha256":"3fc499315c8c01bb636e30e32010fe8429e900c5aa467bbbf954480ce9da32e0","schema_version":"1.0","event_id":"sha256:3fc499315c8c01bb636e30e32010fe8429e900c5aa467bbbf954480ce9da32e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:IISDFV3SI2AXUZHEGY4NQBZHMK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Limitations of Deep Learning in Adversarial Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","stat.ML"],"primary_cat":"cs.CR","authors_text":"Ananthram Swami, Matt Fredrikson, Nicolas Papernot, Patrick McDaniel, Somesh Jha, Z. Berkay Celik","submitted_at":"2015-11-24T01:07:08Z","abstract_excerpt":"Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make them vulnerable to adversarial samples: inputs crafted by adversaries with the intent of causing deep neural networks to misclassify. In this work, we formalize the space of adversaries against deep neural networks (DNNs) and introduce a novel class of algorithms to craft adversarial samples based on a precise understanding of the mapping between inputs and ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07528","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":"2026-05-18T01:26:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d4+aAOlqSObwb79JkTcOIUPZ4c4Bb2+I53zOBwLnM0QLZg5g5/C8ovleMf6zKwPCAWjo9bU8kMhXeGJLpfYMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T03:21:29.581498Z"},"content_sha256":"ba39d291ad44f1cb63076623fd93e24d90afc117d95094c47567a509aab55ef1","schema_version":"1.0","event_id":"sha256:ba39d291ad44f1cb63076623fd93e24d90afc117d95094c47567a509aab55ef1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IISDFV3SI2AXUZHEGY4NQBZHMK/bundle.json","state_url":"https://pith.science/pith/IISDFV3SI2AXUZHEGY4NQBZHMK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IISDFV3SI2AXUZHEGY4NQBZHMK/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":"2026-05-27T03:21:29Z","links":{"resolver":"https://pith.science/pith/IISDFV3SI2AXUZHEGY4NQBZHMK","bundle":"https://pith.science/pith/IISDFV3SI2AXUZHEGY4NQBZHMK/bundle.json","state":"https://pith.science/pith/IISDFV3SI2AXUZHEGY4NQBZHMK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IISDFV3SI2AXUZHEGY4NQBZHMK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:IISDFV3SI2AXUZHEGY4NQBZHMK","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":"ab5790796d3bf532e4641e84f743ac9bf735fcb8e18602859b18c54c584f19e5","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2015-11-24T01:07:08Z","title_canon_sha256":"499e81f45f7558040864f75e20168234642fd51d17f9d5d216600cc6a048405a"},"schema_version":"1.0","source":{"id":"1511.07528","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.07528","created_at":"2026-05-18T01:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"1511.07528v1","created_at":"2026-05-18T01:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.07528","created_at":"2026-05-18T01:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"IISDFV3SI2AX","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"IISDFV3SI2AXUZHE","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"IISDFV3S","created_at":"2026-05-18T12:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:ba39d291ad44f1cb63076623fd93e24d90afc117d95094c47567a509aab55ef1","target":"graph","created_at":"2026-05-18T01:26:04Z","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":"Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make them vulnerable to adversarial samples: inputs crafted by adversaries with the intent of causing deep neural networks to misclassify. In this work, we formalize the space of adversaries against deep neural networks (DNNs) and introduce a novel class of algorithms to craft adversarial samples based on a precise understanding of the mapping between inputs and ou","authors_text":"Ananthram Swami, Matt Fredrikson, Nicolas Papernot, Patrick McDaniel, Somesh Jha, Z. Berkay Celik","cross_cats":["cs.LG","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2015-11-24T01:07:08Z","title":"The Limitations of Deep Learning in Adversarial Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.07528","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":"sha256:3fc499315c8c01bb636e30e32010fe8429e900c5aa467bbbf954480ce9da32e0","target":"record","created_at":"2026-05-18T01:26:04Z","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":"ab5790796d3bf532e4641e84f743ac9bf735fcb8e18602859b18c54c584f19e5","cross_cats_sorted":["cs.LG","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2015-11-24T01:07:08Z","title_canon_sha256":"499e81f45f7558040864f75e20168234642fd51d17f9d5d216600cc6a048405a"},"schema_version":"1.0","source":{"id":"1511.07528","kind":"arxiv","version":1}},"canonical_sha256":"422432d77246817a64e43638d8072762b9dc7b73684c7db70c416cbbe578a90f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"422432d77246817a64e43638d8072762b9dc7b73684c7db70c416cbbe578a90f","first_computed_at":"2026-05-18T01:26:04.540994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:26:04.540994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YLl62KhZXawr7la6JWcEAKv8u9tJU7eBYr5bwIFJxaTAUr47GDkRGHvbvOrVOZIaLT4P5XH9owV98xuno1lPCw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:26:04.541555Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.07528","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fc499315c8c01bb636e30e32010fe8429e900c5aa467bbbf954480ce9da32e0","sha256:ba39d291ad44f1cb63076623fd93e24d90afc117d95094c47567a509aab55ef1"],"state_sha256":"3db809b87b22bb549ca6897c25cc15672c91034b4255450cf4c19748a2aaa2cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qCQdClDkEGmDXuBXTxui65TkwZrssHLtionC0SW+15cfaDa8keK1zh21+paGJjylHfULLlwWNCh+JU2GArZ+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T03:21:29.583806Z","bundle_sha256":"f7970aa76d4fc2b266ef4e36549fe048b087e7c08f7850d667db160c92af58e7"}}