{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5QRW3OWHINAJMQ7QIJ6UKPBOA3","short_pith_number":"pith:5QRW3OWH","schema_version":"1.0","canonical_sha256":"ec236dbac743409643f0427d453c2e06e4c4b610947be1fd728787b4dbbf8416","source":{"kind":"arxiv","id":"2409.12379","version":1},"attestation_state":"computed","paper":{"title":"Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.RO","math.IT"],"primary_cat":"cs.CV","authors_text":"Amit Ranjan Trivedi, Devashri Naik, Dinithi Jayasuriya, Nastaran Darabi, Theja Tulabandhula","submitted_at":"2024-09-19T00:44:45Z","abstract_excerpt":"Adversarial attacks exploit vulnerabilities in a model's decision boundaries through small, carefully crafted perturbations that lead to significant mispredictions. In 3D vision, the high dimensionality and sparsity of data greatly expand the attack surface, making 3D vision particularly vulnerable for safety-critical robotics. To enhance 3D vision's adversarial robustness, we propose a training objective that simultaneously minimizes prediction loss and mutual information (MI) under adversarial perturbations to contain the upper bound of misprediction errors. This approach simplifies handling"},"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":"2409.12379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-19T00:44:45Z","cross_cats_sorted":["cs.IT","cs.RO","math.IT"],"title_canon_sha256":"90983d4283d412a311a72777a7be033bbe5ea012693f91022aba805a34fcc184","abstract_canon_sha256":"eea578e2e623a41fb75decb631ee82c5b852e76d68ca209cee64a826166a7828"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:53.013364Z","signature_b64":"L6T3XaipDLZpos3zcYz/yBDfe6wPZFA5cZQYpuEIvpAqaQuBy5Ld48EBXLYECj2JLNbyjHXBsgm9YSQrOiYJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec236dbac743409643f0427d453c2e06e4c4b610947be1fd728787b4dbbf8416","last_reissued_at":"2026-07-05T09:08:53.012933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:53.012933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.RO","math.IT"],"primary_cat":"cs.CV","authors_text":"Amit Ranjan Trivedi, Devashri Naik, Dinithi Jayasuriya, Nastaran Darabi, Theja Tulabandhula","submitted_at":"2024-09-19T00:44:45Z","abstract_excerpt":"Adversarial attacks exploit vulnerabilities in a model's decision boundaries through small, carefully crafted perturbations that lead to significant mispredictions. In 3D vision, the high dimensionality and sparsity of data greatly expand the attack surface, making 3D vision particularly vulnerable for safety-critical robotics. To enhance 3D vision's adversarial robustness, we propose a training objective that simultaneously minimizes prediction loss and mutual information (MI) under adversarial perturbations to contain the upper bound of misprediction errors. This approach simplifies handling"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12379","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/2409.12379/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":"2409.12379","created_at":"2026-07-05T09:08:53.013004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12379v1","created_at":"2026-07-05T09:08:53.013004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12379","created_at":"2026-07-05T09:08:53.013004+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QRW3OWHINAJ","created_at":"2026-07-05T09:08:53.013004+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QRW3OWHINAJMQ7Q","created_at":"2026-07-05T09:08:53.013004+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QRW3OWH","created_at":"2026-07-05T09:08:53.013004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.01896","citing_title":"INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomy","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QRW3OWHINAJMQ7QIJ6UKPBOA3","json":"https://pith.science/pith/5QRW3OWHINAJMQ7QIJ6UKPBOA3.json","graph_json":"https://pith.science/api/pith-number/5QRW3OWHINAJMQ7QIJ6UKPBOA3/graph.json","events_json":"https://pith.science/api/pith-number/5QRW3OWHINAJMQ7QIJ6UKPBOA3/events.json","paper":"https://pith.science/paper/5QRW3OWH"},"agent_actions":{"view_html":"https://pith.science/pith/5QRW3OWHINAJMQ7QIJ6UKPBOA3","download_json":"https://pith.science/pith/5QRW3OWHINAJMQ7QIJ6UKPBOA3.json","view_paper":"https://pith.science/paper/5QRW3OWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12379&json=true","fetch_graph":"https://pith.science/api/pith-number/5QRW3OWHINAJMQ7QIJ6UKPBOA3/graph.json","fetch_events":"https://pith.science/api/pith-number/5QRW3OWHINAJMQ7QIJ6UKPBOA3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QRW3OWHINAJMQ7QIJ6UKPBOA3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QRW3OWHINAJMQ7QIJ6UKPBOA3/action/storage_attestation","attest_author":"https://pith.science/pith/5QRW3OWHINAJMQ7QIJ6UKPBOA3/action/author_attestation","sign_citation":"https://pith.science/pith/5QRW3OWHINAJMQ7QIJ6UKPBOA3/action/citation_signature","submit_replication":"https://pith.science/pith/5QRW3OWHINAJMQ7QIJ6UKPBOA3/action/replication_record"}},"created_at":"2026-07-05T09:08:53.013004+00:00","updated_at":"2026-07-05T09:08:53.013004+00:00"}