{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:R7XOIGO6HNEQGIBJQBQ6SEXOOO","short_pith_number":"pith:R7XOIGO6","schema_version":"1.0","canonical_sha256":"8feee419de3b490320298061e912ee738fb8fbdb69673702c994900d3e6076cb","source":{"kind":"arxiv","id":"2002.11821","version":1},"attestation_state":"computed","paper":{"title":"Improving Robustness of Deep-Learning-Based Image Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ankit Raj, Bo Li, Yoram Bresler","submitted_at":"2020-02-26T22:12:36Z","abstract_excerpt":"Deep-learning-based methods for different applications have been shown vulnerable to adversarial examples. These examples make deployment of such models in safety-critical tasks questionable. Use of deep neural networks as inverse problem solvers has generated much excitement for medical imaging including CT and MRI, but recently a similar vulnerability has also been demonstrated for these tasks. We show that for such inverse problem solvers, one should analyze and study the effect of adversaries in the measurement-space, instead of the signal-space as in previous work. In this paper, we propo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2002.11821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-26T22:12:36Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"d9c83da98e55efabac62820c6994368926a46d3aff5fcca4a236e8f94ffb74a7","abstract_canon_sha256":"483a1f040ca8b44100bffbb61ad7eaf0cc792d32a6fc2c78e0b6435f58b4dc86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:09.337305Z","signature_b64":"EDafGTSkgpJBbSNK+IPMMj4h39/Bjkbid+GBmWbNbfbQ3TcGx3FnG7yOSoBpgP0vhNvgvJJK1lGbFWwaYPwxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8feee419de3b490320298061e912ee738fb8fbdb69673702c994900d3e6076cb","last_reissued_at":"2026-07-05T00:44:09.336791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:09.336791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Robustness of Deep-Learning-Based Image Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ankit Raj, Bo Li, Yoram Bresler","submitted_at":"2020-02-26T22:12:36Z","abstract_excerpt":"Deep-learning-based methods for different applications have been shown vulnerable to adversarial examples. These examples make deployment of such models in safety-critical tasks questionable. Use of deep neural networks as inverse problem solvers has generated much excitement for medical imaging including CT and MRI, but recently a similar vulnerability has also been demonstrated for these tasks. We show that for such inverse problem solvers, one should analyze and study the effect of adversaries in the measurement-space, instead of the signal-space as in previous work. In this paper, we propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11821","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/2002.11821/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2002.11821","created_at":"2026-07-05T00:44:09.336851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.11821v1","created_at":"2026-07-05T00:44:09.336851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11821","created_at":"2026-07-05T00:44:09.336851+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7XOIGO6HNEQ","created_at":"2026-07-05T00:44:09.336851+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7XOIGO6HNEQGIBJ","created_at":"2026-07-05T00:44:09.336851+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7XOIGO6","created_at":"2026-07-05T00:44:09.336851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15150","citing_title":"Leveraging Color Channel Independence for Improved Unsupervised Object Detection","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R7XOIGO6HNEQGIBJQBQ6SEXOOO","json":"https://pith.science/pith/R7XOIGO6HNEQGIBJQBQ6SEXOOO.json","graph_json":"https://pith.science/api/pith-number/R7XOIGO6HNEQGIBJQBQ6SEXOOO/graph.json","events_json":"https://pith.science/api/pith-number/R7XOIGO6HNEQGIBJQBQ6SEXOOO/events.json","paper":"https://pith.science/paper/R7XOIGO6"},"agent_actions":{"view_html":"https://pith.science/pith/R7XOIGO6HNEQGIBJQBQ6SEXOOO","download_json":"https://pith.science/pith/R7XOIGO6HNEQGIBJQBQ6SEXOOO.json","view_paper":"https://pith.science/paper/R7XOIGO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.11821&json=true","fetch_graph":"https://pith.science/api/pith-number/R7XOIGO6HNEQGIBJQBQ6SEXOOO/graph.json","fetch_events":"https://pith.science/api/pith-number/R7XOIGO6HNEQGIBJQBQ6SEXOOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7XOIGO6HNEQGIBJQBQ6SEXOOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7XOIGO6HNEQGIBJQBQ6SEXOOO/action/storage_attestation","attest_author":"https://pith.science/pith/R7XOIGO6HNEQGIBJQBQ6SEXOOO/action/author_attestation","sign_citation":"https://pith.science/pith/R7XOIGO6HNEQGIBJQBQ6SEXOOO/action/citation_signature","submit_replication":"https://pith.science/pith/R7XOIGO6HNEQGIBJQBQ6SEXOOO/action/replication_record"}},"created_at":"2026-07-05T00:44:09.336851+00:00","updated_at":"2026-07-05T00:44:09.336851+00:00"}