{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GXNI7ZVOHLH7OPDH5M4KNWOCLR","short_pith_number":"pith:GXNI7ZVO","schema_version":"1.0","canonical_sha256":"35da8fe6ae3acff73c67eb38a6d9c25c6d742788b28dc203368c086f84424224","source":{"kind":"arxiv","id":"1707.07397","version":3},"attestation_state":"computed","paper":{"title":"Synthesizing Robust Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Ilyas, Anish Athalye, Kevin Kwok, Logan Engstrom","submitted_at":"2017-07-24T04:17:33Z","abstract_excerpt":"Standard methods for generating adversarial examples for neural networks do not consistently fool neural network classifiers in the physical world due to a combination of viewpoint shifts, camera noise, and other natural transformations, limiting their relevance to real-world systems. We demonstrate the existence of robust 3D adversarial objects, and we present the first algorithm for synthesizing examples that are adversarial over a chosen distribution of transformations. We synthesize two-dimensional adversarial images that are robust to noise, distortion, and affine transformation. We apply"},"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":"1707.07397","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-24T04:17:33Z","cross_cats_sorted":[],"title_canon_sha256":"4b509b0d462aada0299551c77e615f4ffc95f38ab8e5ebcffcc34939e0f4320c","abstract_canon_sha256":"f546d6004a55e98ad8b0a7ea7516e922d8432fcaafe86150ccfa00825c3a387c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:00.991038Z","signature_b64":"IRhiC9pGDfOm+JNtzhELlJ9arCMls+W7TZqP348Wzzr7KUcoSVUpx6LrqxlrCZ3G/8VJBXWQTAGv5lZ8/7FuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35da8fe6ae3acff73c67eb38a6d9c25c6d742788b28dc203368c086f84424224","last_reissued_at":"2026-05-18T00:14:00.990462Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:00.990462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthesizing Robust Adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Ilyas, Anish Athalye, Kevin Kwok, Logan Engstrom","submitted_at":"2017-07-24T04:17:33Z","abstract_excerpt":"Standard methods for generating adversarial examples for neural networks do not consistently fool neural network classifiers in the physical world due to a combination of viewpoint shifts, camera noise, and other natural transformations, limiting their relevance to real-world systems. We demonstrate the existence of robust 3D adversarial objects, and we present the first algorithm for synthesizing examples that are adversarial over a chosen distribution of transformations. We synthesize two-dimensional adversarial images that are robust to noise, distortion, and affine transformation. We apply"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07397","kind":"arxiv","version":3},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1707.07397","created_at":"2026-05-18T00:14:00.990548+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.07397v3","created_at":"2026-05-18T00:14:00.990548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07397","created_at":"2026-05-18T00:14:00.990548+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXNI7ZVOHLH7","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXNI7ZVOHLH7OPDH","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXNI7ZVO","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"1906.10671","citing_title":"Explaining Deep Learning Models with Constrained Adversarial Examples","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00374","citing_title":"Fooling a Real Car with Adversarial Traffic Signs","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20519","citing_title":"Codec-Robust Attacks on Audio LLMs","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05274","citing_title":"Affine Disentangled GAN for Interpretable and Robust AV Perception","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05418","citing_title":"Adversarial Objects Against LiDAR-Based Autonomous Driving Systems","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06374","citing_title":"What does it mean to understand a neural network?","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20519","citing_title":"Codec-Robust Attacks on Audio LLMs","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07379","citing_title":"RELO: Reinforcement Learning to Localize for Visual Object Tracking","ref_index":198,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06357","citing_title":"Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluations","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07379","citing_title":"RELO: Reinforcement Learning to Localize for Visual Object Tracking","ref_index":197,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXNI7ZVOHLH7OPDH5M4KNWOCLR","json":"https://pith.science/pith/GXNI7ZVOHLH7OPDH5M4KNWOCLR.json","graph_json":"https://pith.science/api/pith-number/GXNI7ZVOHLH7OPDH5M4KNWOCLR/graph.json","events_json":"https://pith.science/api/pith-number/GXNI7ZVOHLH7OPDH5M4KNWOCLR/events.json","paper":"https://pith.science/paper/GXNI7ZVO"},"agent_actions":{"view_html":"https://pith.science/pith/GXNI7ZVOHLH7OPDH5M4KNWOCLR","download_json":"https://pith.science/pith/GXNI7ZVOHLH7OPDH5M4KNWOCLR.json","view_paper":"https://pith.science/paper/GXNI7ZVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.07397&json=true","fetch_graph":"https://pith.science/api/pith-number/GXNI7ZVOHLH7OPDH5M4KNWOCLR/graph.json","fetch_events":"https://pith.science/api/pith-number/GXNI7ZVOHLH7OPDH5M4KNWOCLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXNI7ZVOHLH7OPDH5M4KNWOCLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXNI7ZVOHLH7OPDH5M4KNWOCLR/action/storage_attestation","attest_author":"https://pith.science/pith/GXNI7ZVOHLH7OPDH5M4KNWOCLR/action/author_attestation","sign_citation":"https://pith.science/pith/GXNI7ZVOHLH7OPDH5M4KNWOCLR/action/citation_signature","submit_replication":"https://pith.science/pith/GXNI7ZVOHLH7OPDH5M4KNWOCLR/action/replication_record"}},"created_at":"2026-05-18T00:14:00.990548+00:00","updated_at":"2026-05-18T00:14:00.990548+00:00"}