{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:U3BI2ICN4VBNJJGJ3BWGGKC5PR","short_pith_number":"pith:U3BI2ICN","schema_version":"1.0","canonical_sha256":"a6c28d204de542d4a4c9d86c63285d7c7e9faafd92f309e8370894feb02ffbcf","source":{"kind":"arxiv","id":"1803.10840","version":3},"attestation_state":"computed","paper":{"title":"Defending against Adversarial Images using Basis Functions Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alex Cloninger, Ethan Weinberger, James Garritano, Kelly Stanton, Uri Shaham, Xiuyuan Cheng, Yutaro Yamada, Yuval Kluger","submitted_at":"2018-03-28T20:27:58Z","abstract_excerpt":"We study the effectiveness of various approaches that defend against adversarial attacks on deep networks via manipulations based on basis function representations of images. Specifically, we experiment with low-pass filtering, PCA, JPEG compression, low resolution wavelet approximation, and soft-thresholding. We evaluate these defense techniques using three types of popular attacks in black, gray and white-box settings. Our results show JPEG compression tends to outperform the other tested defenses in most of the settings considered, in addition to soft-thresholding, which performs well in sp"},"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":"1803.10840","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-28T20:27:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"024d390fae973389333fdbfd7d86b772b5a323c4e17b8f0ab45d3a26317118d7","abstract_canon_sha256":"e845a54381f0959c3d3b4778d6fdd6949739279a99ce874a5e641beaa8afec73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:25.097658Z","signature_b64":"eXepMe+7wmatK6vEcKStnE16BukpABUL4h/var/2DsUaXsH9TCF9lheYUXnhquKQXY3XCEU4WqkQxk8H1+wSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6c28d204de542d4a4c9d86c63285d7c7e9faafd92f309e8370894feb02ffbcf","last_reissued_at":"2026-05-18T00:18:25.097121Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:25.097121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Defending against Adversarial Images using Basis Functions Transformations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alex Cloninger, Ethan Weinberger, James Garritano, Kelly Stanton, Uri Shaham, Xiuyuan Cheng, Yutaro Yamada, Yuval Kluger","submitted_at":"2018-03-28T20:27:58Z","abstract_excerpt":"We study the effectiveness of various approaches that defend against adversarial attacks on deep networks via manipulations based on basis function representations of images. Specifically, we experiment with low-pass filtering, PCA, JPEG compression, low resolution wavelet approximation, and soft-thresholding. We evaluate these defense techniques using three types of popular attacks in black, gray and white-box settings. Our results show JPEG compression tends to outperform the other tested defenses in most of the settings considered, in addition to soft-thresholding, which performs well in sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10840","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":"1803.10840","created_at":"2026-05-18T00:18:25.097192+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.10840v3","created_at":"2026-05-18T00:18:25.097192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10840","created_at":"2026-05-18T00:18:25.097192+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3BI2ICN4VBN","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3BI2ICN4VBNJJGJ","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3BI2ICN","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U3BI2ICN4VBNJJGJ3BWGGKC5PR","json":"https://pith.science/pith/U3BI2ICN4VBNJJGJ3BWGGKC5PR.json","graph_json":"https://pith.science/api/pith-number/U3BI2ICN4VBNJJGJ3BWGGKC5PR/graph.json","events_json":"https://pith.science/api/pith-number/U3BI2ICN4VBNJJGJ3BWGGKC5PR/events.json","paper":"https://pith.science/paper/U3BI2ICN"},"agent_actions":{"view_html":"https://pith.science/pith/U3BI2ICN4VBNJJGJ3BWGGKC5PR","download_json":"https://pith.science/pith/U3BI2ICN4VBNJJGJ3BWGGKC5PR.json","view_paper":"https://pith.science/paper/U3BI2ICN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.10840&json=true","fetch_graph":"https://pith.science/api/pith-number/U3BI2ICN4VBNJJGJ3BWGGKC5PR/graph.json","fetch_events":"https://pith.science/api/pith-number/U3BI2ICN4VBNJJGJ3BWGGKC5PR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3BI2ICN4VBNJJGJ3BWGGKC5PR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3BI2ICN4VBNJJGJ3BWGGKC5PR/action/storage_attestation","attest_author":"https://pith.science/pith/U3BI2ICN4VBNJJGJ3BWGGKC5PR/action/author_attestation","sign_citation":"https://pith.science/pith/U3BI2ICN4VBNJJGJ3BWGGKC5PR/action/citation_signature","submit_replication":"https://pith.science/pith/U3BI2ICN4VBNJJGJ3BWGGKC5PR/action/replication_record"}},"created_at":"2026-05-18T00:18:25.097192+00:00","updated_at":"2026-05-18T00:18:25.097192+00:00"}