{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:ENPD7AT73B2QHZ4SOJMP2OOCXB","short_pith_number":"pith:ENPD7AT7","schema_version":"1.0","canonical_sha256":"235e3f827fd87503e7927258fd39c2b8731a2025884022099b020caa8e9aeb10","source":{"kind":"arxiv","id":"1502.07661","version":1},"attestation_state":"computed","paper":{"title":"Detecting Malware with Information Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC"],"primary_cat":"cs.CR","authors_text":"David Clark, Earl T. Barr, George Danezis, Nadia Alshahwan","submitted_at":"2015-02-26T18:21:07Z","abstract_excerpt":"This work focuses on a specific front of the malware detection arms-race, namely the detection of persistent, disk-resident malware. We exploit normalised compression distance (NCD), an information theoretic measure, applied directly to binaries. Given a zoo of labelled malware and benign-ware, we ask whether a suspect program is more similar to our malware or to our benign-ware. Our approach classifies malware with 97.1% accuracy and a false positive rate of 3%. We achieve our results with off-the-shelf compressors and a standard machine learning classifier and without any specialised knowled"},"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":"1502.07661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2015-02-26T18:21:07Z","cross_cats_sorted":["cs.CC"],"title_canon_sha256":"b0c7b585957d936c530787edf8c8701f72bf3bb96ee8a3ae799c2c86243b947c","abstract_canon_sha256":"2b9ad4bb36694b5bc3117b653ca58d29519993062326dd344e5aaedbb7cf50aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:26:03.184737Z","signature_b64":"7TtrSCSn7OtPkzULQ8kjl2m/ujDqTXNTP6nSgqi+zkVHh5IRgUs5PL2zJVPp/2Ciw3Hu0UBLQ+huEvxGHek4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"235e3f827fd87503e7927258fd39c2b8731a2025884022099b020caa8e9aeb10","last_reissued_at":"2026-05-18T02:26:03.184325Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:26:03.184325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting Malware with Information Complexity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC"],"primary_cat":"cs.CR","authors_text":"David Clark, Earl T. Barr, George Danezis, Nadia Alshahwan","submitted_at":"2015-02-26T18:21:07Z","abstract_excerpt":"This work focuses on a specific front of the malware detection arms-race, namely the detection of persistent, disk-resident malware. We exploit normalised compression distance (NCD), an information theoretic measure, applied directly to binaries. Given a zoo of labelled malware and benign-ware, we ask whether a suspect program is more similar to our malware or to our benign-ware. Our approach classifies malware with 97.1% accuracy and a false positive rate of 3%. We achieve our results with off-the-shelf compressors and a standard machine learning classifier and without any specialised knowled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.07661","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":""},"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":"1502.07661","created_at":"2026-05-18T02:26:03.184385+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.07661v1","created_at":"2026-05-18T02:26:03.184385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.07661","created_at":"2026-05-18T02:26:03.184385+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENPD7AT73B2Q","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENPD7AT73B2QHZ4S","created_at":"2026-05-18T12:29:19.899920+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENPD7AT7","created_at":"2026-05-18T12:29:19.899920+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/ENPD7AT73B2QHZ4SOJMP2OOCXB","json":"https://pith.science/pith/ENPD7AT73B2QHZ4SOJMP2OOCXB.json","graph_json":"https://pith.science/api/pith-number/ENPD7AT73B2QHZ4SOJMP2OOCXB/graph.json","events_json":"https://pith.science/api/pith-number/ENPD7AT73B2QHZ4SOJMP2OOCXB/events.json","paper":"https://pith.science/paper/ENPD7AT7"},"agent_actions":{"view_html":"https://pith.science/pith/ENPD7AT73B2QHZ4SOJMP2OOCXB","download_json":"https://pith.science/pith/ENPD7AT73B2QHZ4SOJMP2OOCXB.json","view_paper":"https://pith.science/paper/ENPD7AT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.07661&json=true","fetch_graph":"https://pith.science/api/pith-number/ENPD7AT73B2QHZ4SOJMP2OOCXB/graph.json","fetch_events":"https://pith.science/api/pith-number/ENPD7AT73B2QHZ4SOJMP2OOCXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENPD7AT73B2QHZ4SOJMP2OOCXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENPD7AT73B2QHZ4SOJMP2OOCXB/action/storage_attestation","attest_author":"https://pith.science/pith/ENPD7AT73B2QHZ4SOJMP2OOCXB/action/author_attestation","sign_citation":"https://pith.science/pith/ENPD7AT73B2QHZ4SOJMP2OOCXB/action/citation_signature","submit_replication":"https://pith.science/pith/ENPD7AT73B2QHZ4SOJMP2OOCXB/action/replication_record"}},"created_at":"2026-05-18T02:26:03.184385+00:00","updated_at":"2026-05-18T02:26:03.184385+00:00"}