{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BWTCW26MWMNACU5OYW6Y646XIA","short_pith_number":"pith:BWTCW26M","schema_version":"1.0","canonical_sha256":"0da62b6bccb31a0153aec5bd8f73d7403aa31bd4b86ed614d5e21b769d83a4d6","source":{"kind":"arxiv","id":"2010.01950","version":3},"attestation_state":"computed","paper":{"title":"Torchattacks: A PyTorch Repository for Adversarial Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Hoki Kim","submitted_at":"2020-09-24T01:34:42Z","abstract_excerpt":"Torchattacks is a PyTorch library that contains adversarial attacks to generate adversarial examples and to verify the robustness of deep learning models. The code can be found at https://github.com/Harry24k/adversarial-attacks-pytorch."},"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":"2010.01950","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-24T01:34:42Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"8658b289de008cf8e42f70e2e9f2f9c458dbbb546074b65355780aaa78fbe28c","abstract_canon_sha256":"761676fa22baa1ab41dc75bca36f981395754ccc9cfa5e7e844127ef5751a39e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:37.826226Z","signature_b64":"LfMhMy0E6mas+uLng2hhG5QY1l55+4spQwOzgJcDjprKCfnXXaBoSn3gYZBTkJaGKFMdxPYehVHATT7XC/t5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0da62b6bccb31a0153aec5bd8f73d7403aa31bd4b86ed614d5e21b769d83a4d6","last_reissued_at":"2026-07-05T02:16:37.825866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:37.825866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Torchattacks: A PyTorch Repository for Adversarial Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Hoki Kim","submitted_at":"2020-09-24T01:34:42Z","abstract_excerpt":"Torchattacks is a PyTorch library that contains adversarial attacks to generate adversarial examples and to verify the robustness of deep learning models. The code can be found at https://github.com/Harry24k/adversarial-attacks-pytorch."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01950","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.01950/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":"2010.01950","created_at":"2026-07-05T02:16:37.825926+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01950v3","created_at":"2026-07-05T02:16:37.825926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01950","created_at":"2026-07-05T02:16:37.825926+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWTCW26MWMNA","created_at":"2026-07-05T02:16:37.825926+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWTCW26MWMNACU5O","created_at":"2026-07-05T02:16:37.825926+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWTCW26M","created_at":"2026-07-05T02:16:37.825926+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05748","citing_title":"Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02267","citing_title":"A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30342","citing_title":"A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30342","citing_title":"A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2410.03000","citing_title":"Towards Generalized Certified Robustness with Multi-Norm Training","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2503.02574","citing_title":"LLM-Safety Evaluations Lack Robustness","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17577","citing_title":"TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21879","citing_title":"Learning Aligned Stability in Neural ODEs Reconciling Accuracy with Robustness","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27487","citing_title":"Low Rank Adaptation for Adversarial Perturbation","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10933","citing_title":"QShield: Securing Neural Networks Against Adversarial Attacks using Quantum Circuits","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BWTCW26MWMNACU5OYW6Y646XIA","json":"https://pith.science/pith/BWTCW26MWMNACU5OYW6Y646XIA.json","graph_json":"https://pith.science/api/pith-number/BWTCW26MWMNACU5OYW6Y646XIA/graph.json","events_json":"https://pith.science/api/pith-number/BWTCW26MWMNACU5OYW6Y646XIA/events.json","paper":"https://pith.science/paper/BWTCW26M"},"agent_actions":{"view_html":"https://pith.science/pith/BWTCW26MWMNACU5OYW6Y646XIA","download_json":"https://pith.science/pith/BWTCW26MWMNACU5OYW6Y646XIA.json","view_paper":"https://pith.science/paper/BWTCW26M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01950&json=true","fetch_graph":"https://pith.science/api/pith-number/BWTCW26MWMNACU5OYW6Y646XIA/graph.json","fetch_events":"https://pith.science/api/pith-number/BWTCW26MWMNACU5OYW6Y646XIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWTCW26MWMNACU5OYW6Y646XIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWTCW26MWMNACU5OYW6Y646XIA/action/storage_attestation","attest_author":"https://pith.science/pith/BWTCW26MWMNACU5OYW6Y646XIA/action/author_attestation","sign_citation":"https://pith.science/pith/BWTCW26MWMNACU5OYW6Y646XIA/action/citation_signature","submit_replication":"https://pith.science/pith/BWTCW26MWMNACU5OYW6Y646XIA/action/replication_record"}},"created_at":"2026-07-05T02:16:37.825926+00:00","updated_at":"2026-07-05T02:16:37.825926+00:00"}