{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:BM6LKQT5XOUYJ4KFAXQUF7SW4Q","short_pith_number":"pith:BM6LKQT5","canonical_record":{"source":{"id":"1804.05805","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-16T17:24:51Z","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"title_canon_sha256":"5fdfdca08fd3b03e0350487652ad02ad4f0c59051c7c0e38f8f49cc4726a88e4","abstract_canon_sha256":"65c5f2cf1e5809c6c9ee33cd089302186c1f867881ec11e27ab77ae2785550a6"},"schema_version":"1.0"},"canonical_sha256":"0b3cb5427dbba984f14505e142fe56e40e77839674ad0ee959d2f673d8b4eda3","source":{"kind":"arxiv","id":"1804.05805","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.05805","created_at":"2026-05-18T00:00:21Z"},{"alias_kind":"arxiv_version","alias_value":"1804.05805v2","created_at":"2026-05-18T00:00:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05805","created_at":"2026-05-18T00:00:21Z"},{"alias_kind":"pith_short_12","alias_value":"BM6LKQT5XOUY","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BM6LKQT5XOUYJ4KF","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BM6LKQT5","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:BM6LKQT5XOUYJ4KFAXQUF7SW4Q","target":"record","payload":{"canonical_record":{"source":{"id":"1804.05805","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-16T17:24:51Z","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"title_canon_sha256":"5fdfdca08fd3b03e0350487652ad02ad4f0c59051c7c0e38f8f49cc4726a88e4","abstract_canon_sha256":"65c5f2cf1e5809c6c9ee33cd089302186c1f867881ec11e27ab77ae2785550a6"},"schema_version":"1.0"},"canonical_sha256":"0b3cb5427dbba984f14505e142fe56e40e77839674ad0ee959d2f673d8b4eda3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:21.536195Z","signature_b64":"YL7+jWjdmkafOfj099Gonphc0Rz1zW9njr5sGl6pVCLmdjzO0gPZSQfWROGVmLIEzBY0BGNBvR9Vl1bNPfN8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b3cb5427dbba984f14505e142fe56e40e77839674ad0ee959d2f673d8b4eda3","last_reissued_at":"2026-05-18T00:00:21.535555Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:21.535555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.05805","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":"2026-05-18T00:00:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MJkrxsG8oICEgbUw/unqo9EcZ32KCgFL3RcQVFQclyd1BwCjNznriY7TOa7CACICC5fshYAh5Xrvk+JgJAzOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:16:10.045451Z"},"content_sha256":"b89da7e9f7413e082e1e6c0e9a359f648c17cfc6169d3e2842b593666e160b37","schema_version":"1.0","event_id":"sha256:b89da7e9f7413e082e1e6c0e9a359f648c17cfc6169d3e2842b593666e160b37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:BM6LKQT5XOUYJ4KFAXQUF7SW4Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the $L_0$ Norm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Kroening, Marta Kwiatkowska, Min Wu, Wenjie Ruan, Xiaowei Huang, Youcheng Sun","submitted_at":"2018-04-16T17:24:51Z","abstract_excerpt":"Deployment of deep neural networks (DNNs) in safety- or security-critical systems requires provable guarantees on their correct behaviour. A common requirement is robustness to adversarial perturbations in a neighbourhood around an input. In this paper we focus on the $L_0$ norm and aim to compute, for a trained DNN and an input, the maximal radius of a safe norm ball around the input within which there are no adversarial examples. Then we define global robustness as an expectation of the maximal safe radius over a test data set. We first show that the problem is NP-hard, and then propose an a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05805","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":""},"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":"2026-05-18T00:00:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C6HhhlnrDmJ18OEVi+2VjbSfojxPS/5W5Leg0zWDYjNjBXdFLyYWXQpBl/yC0BffhZPNcfXIQMXRB3r0s6t5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:16:10.046054Z"},"content_sha256":"357ae86a3aaa8aaca756e4c9c1fde81365b20948c37e06dd4ac532987de88fec","schema_version":"1.0","event_id":"sha256:357ae86a3aaa8aaca756e4c9c1fde81365b20948c37e06dd4ac532987de88fec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BM6LKQT5XOUYJ4KFAXQUF7SW4Q/bundle.json","state_url":"https://pith.science/pith/BM6LKQT5XOUYJ4KFAXQUF7SW4Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BM6LKQT5XOUYJ4KFAXQUF7SW4Q/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":"2026-05-28T13:16:10Z","links":{"resolver":"https://pith.science/pith/BM6LKQT5XOUYJ4KFAXQUF7SW4Q","bundle":"https://pith.science/pith/BM6LKQT5XOUYJ4KFAXQUF7SW4Q/bundle.json","state":"https://pith.science/pith/BM6LKQT5XOUYJ4KFAXQUF7SW4Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BM6LKQT5XOUYJ4KFAXQUF7SW4Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BM6LKQT5XOUYJ4KFAXQUF7SW4Q","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":"65c5f2cf1e5809c6c9ee33cd089302186c1f867881ec11e27ab77ae2785550a6","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-16T17:24:51Z","title_canon_sha256":"5fdfdca08fd3b03e0350487652ad02ad4f0c59051c7c0e38f8f49cc4726a88e4"},"schema_version":"1.0","source":{"id":"1804.05805","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.05805","created_at":"2026-05-18T00:00:21Z"},{"alias_kind":"arxiv_version","alias_value":"1804.05805v2","created_at":"2026-05-18T00:00:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05805","created_at":"2026-05-18T00:00:21Z"},{"alias_kind":"pith_short_12","alias_value":"BM6LKQT5XOUY","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BM6LKQT5XOUYJ4KF","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BM6LKQT5","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:357ae86a3aaa8aaca756e4c9c1fde81365b20948c37e06dd4ac532987de88fec","target":"graph","created_at":"2026-05-18T00:00:21Z","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":"Deployment of deep neural networks (DNNs) in safety- or security-critical systems requires provable guarantees on their correct behaviour. A common requirement is robustness to adversarial perturbations in a neighbourhood around an input. In this paper we focus on the $L_0$ norm and aim to compute, for a trained DNN and an input, the maximal radius of a safe norm ball around the input within which there are no adversarial examples. Then we define global robustness as an expectation of the maximal safe radius over a test data set. We first show that the problem is NP-hard, and then propose an a","authors_text":"Daniel Kroening, Marta Kwiatkowska, Min Wu, Wenjie Ruan, Xiaowei Huang, Youcheng Sun","cross_cats":["cs.CR","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-16T17:24:51Z","title":"Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the $L_0$ Norm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05805","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:b89da7e9f7413e082e1e6c0e9a359f648c17cfc6169d3e2842b593666e160b37","target":"record","created_at":"2026-05-18T00:00:21Z","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":"65c5f2cf1e5809c6c9ee33cd089302186c1f867881ec11e27ab77ae2785550a6","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-16T17:24:51Z","title_canon_sha256":"5fdfdca08fd3b03e0350487652ad02ad4f0c59051c7c0e38f8f49cc4726a88e4"},"schema_version":"1.0","source":{"id":"1804.05805","kind":"arxiv","version":2}},"canonical_sha256":"0b3cb5427dbba984f14505e142fe56e40e77839674ad0ee959d2f673d8b4eda3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b3cb5427dbba984f14505e142fe56e40e77839674ad0ee959d2f673d8b4eda3","first_computed_at":"2026-05-18T00:00:21.535555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:21.535555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YL7+jWjdmkafOfj099Gonphc0Rz1zW9njr5sGl6pVCLmdjzO0gPZSQfWROGVmLIEzBY0BGNBvR9Vl1bNPfN8Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:21.536195Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.05805","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b89da7e9f7413e082e1e6c0e9a359f648c17cfc6169d3e2842b593666e160b37","sha256:357ae86a3aaa8aaca756e4c9c1fde81365b20948c37e06dd4ac532987de88fec"],"state_sha256":"6050944a11fa264ed05c38b7546bd33761cbb49184bf730399dcd555b619bdc7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5wqGgjVXm/kTUCBu1TjRBl3XVWjKRV5KYHvapaPw4BtRiDhzXWvVqt+54kRixzZTjKWGtNY+4jYs+odyba8ABQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T13:16:10.049155Z","bundle_sha256":"e82ea767f0a645755a87717781dfb6b40f38602e161e15daedd0f6d36c5ceb76"}}