{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GFQ7AU4UXPMWV2UQ6ZYN7DC2WF","short_pith_number":"pith:GFQ7AU4U","schema_version":"1.0","canonical_sha256":"3161f05394bbd96aea90f670df8c5ab145984143fa0348e7eae6268b0d942832","source":{"kind":"arxiv","id":"2505.03147","version":1},"attestation_state":"computed","paper":{"title":"Towards Effective Identification of Attack Techniques in Cyber Threat Intelligence Reports using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Bao Quoc Vo, Hoang Cuong Nguyen, Mohan Baruwal Chhetri, Shahroz Tariq","submitted_at":"2025-05-06T03:43:12Z","abstract_excerpt":"This work evaluates the performance of Cyber Threat Intelligence (CTI) extraction methods in identifying attack techniques from threat reports available on the web using the MITRE ATT&CK framework. We analyse four configurations utilising state-of-the-art tools, including the Threat Report ATT&CK Mapper (TRAM) and open-source Large Language Models (LLMs) such as Llama2. Our findings reveal significant challenges, including class imbalance, overfitting, and domain-specific complexity, which impede accurate technique extraction. To mitigate these issues, we propose a novel two-step pipeline: fir"},"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":"2505.03147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-05-06T03:43:12Z","cross_cats_sorted":[],"title_canon_sha256":"347316feca3a41647153ff42dcb38cc0a72296d82136e171f5bf0de57d823859","abstract_canon_sha256":"318f93146cfc0ffdaf25f1cf2b3339a2c9177e9c50ccea201be8168f62f28e62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:10.874961Z","signature_b64":"1pwLaKERAGXOmO3YYqiBP826lNWePhJBygLUAZcb32jtm31zUkWKSdclKT4zzD8nooDQEodGVgWzSxTxL4emCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3161f05394bbd96aea90f670df8c5ab145984143fa0348e7eae6268b0d942832","last_reissued_at":"2026-07-05T10:59:10.874481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:10.874481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Effective Identification of Attack Techniques in Cyber Threat Intelligence Reports using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Bao Quoc Vo, Hoang Cuong Nguyen, Mohan Baruwal Chhetri, Shahroz Tariq","submitted_at":"2025-05-06T03:43:12Z","abstract_excerpt":"This work evaluates the performance of Cyber Threat Intelligence (CTI) extraction methods in identifying attack techniques from threat reports available on the web using the MITRE ATT&CK framework. We analyse four configurations utilising state-of-the-art tools, including the Threat Report ATT&CK Mapper (TRAM) and open-source Large Language Models (LLMs) such as Llama2. Our findings reveal significant challenges, including class imbalance, overfitting, and domain-specific complexity, which impede accurate technique extraction. To mitigate these issues, we propose a novel two-step pipeline: fir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03147","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/2505.03147/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":"2505.03147","created_at":"2026-07-05T10:59:10.874537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03147v1","created_at":"2026-07-05T10:59:10.874537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03147","created_at":"2026-07-05T10:59:10.874537+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFQ7AU4UXPMW","created_at":"2026-07-05T10:59:10.874537+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFQ7AU4UXPMWV2UQ","created_at":"2026-07-05T10:59:10.874537+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFQ7AU4U","created_at":"2026-07-05T10:59:10.874537+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/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF","json":"https://pith.science/pith/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF.json","graph_json":"https://pith.science/api/pith-number/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF/graph.json","events_json":"https://pith.science/api/pith-number/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF/events.json","paper":"https://pith.science/paper/GFQ7AU4U"},"agent_actions":{"view_html":"https://pith.science/pith/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF","download_json":"https://pith.science/pith/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF.json","view_paper":"https://pith.science/paper/GFQ7AU4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03147&json=true","fetch_graph":"https://pith.science/api/pith-number/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF/graph.json","fetch_events":"https://pith.science/api/pith-number/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF/action/storage_attestation","attest_author":"https://pith.science/pith/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF/action/author_attestation","sign_citation":"https://pith.science/pith/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF/action/citation_signature","submit_replication":"https://pith.science/pith/GFQ7AU4UXPMWV2UQ6ZYN7DC2WF/action/replication_record"}},"created_at":"2026-07-05T10:59:10.874537+00:00","updated_at":"2026-07-05T10:59:10.874537+00:00"}