{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T02:21:00Z","timestamp":1773195660260,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/acsacw69556.2025.00072","type":"proceedings-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T19:56:13Z","timestamp":1773086173000},"page":"443-450","source":"Crossref","is-referenced-by-count":0,"title":["AthenaBench: A Dynamic Benchmark for Evaluating LLMs in Cyber Threat Intelligence"],"prefix":"10.1109","author":[{"given":"Md Tanvirul","family":"Alam","sequence":"first","affiliation":[{"name":"Rochester Institute of Technology,Rochester,NY,USA"}]},{"given":"Dipkamal","family":"Bhusal","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology,Rochester,NY,USA"}]},{"given":"Salman","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Athena Security Group,FL,USA"}]},{"given":"Nidhi","family":"Rastogi","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology,Rochester,NY,USA"}]},{"given":"Peter","family":"Worth","sequence":"additional","affiliation":[{"name":"Athena Security Group,FL,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1607"},{"key":"ref2","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"Neurips"},{"key":"ref3","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref4","author":"Bubeck","year":"2023","journal-title":"Sparks of artificial general intelligence: Early experiments with gpt-4"},{"key":"ref5","article-title":"Definition: threat intelligence","author":"McMillan","year":"2013","journal-title":"Gartner. com"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jisa.2024.103786"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/PESGM51994.2024.10688863"},{"key":"ref8","author":"Yigit","year":"2024","journal-title":"Review of generative ai methods in cybersecurity"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSPW61312.2024.00018"},{"key":"ref10","article-title":"Seceval: A comprehensive benchmark for evaluating cybersecurity knowledge of foundation models","author":"Li","year":"2023"},{"key":"ref11","article-title":"Cyberbench: A multi-task benchmark for evaluating large language models in cybersecurity","volume-title":"AAAI 2024 Workshop on Artificial Intelligence for Cyber Security","author":"Liu"},{"key":"ref12","author":"Liu","year":"2023","journal-title":"Secqa: A concise question-answering dataset for evaluating large language models in computer security"},{"key":"ref13","author":"Ji","year":"2024","journal-title":"Sevenllm: Benchmarking, eliciting, and enhancing abilities of large language models in cyber threat intelligence"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACSAC63791.2024.00019"},{"key":"ref15","article-title":"Navigating the cyber security landscape: A comprehensive review of cyber-attacks, emerging trends, and recent developments","author":"Mallick","year":"2024","journal-title":"World Scientific News"},{"key":"ref16","article-title":"Mitre att&ck: Design and philosophy","author":"Strom","year":"2018","journal-title":"Technical report. The MITRE Corporation"},{"key":"ref17","volume-title":"National vulnerability database","year":"2025"},{"key":"ref18","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref19","volume-title":"Gpt-4o model openai","year":"2024"},{"key":"ref20","volume-title":"Gpt-5 model openai","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.51644\/9781771120920-031"},{"key":"ref22","article-title":"Qwen3 technical report","year":"2025"},{"key":"ref23","volume-title":"Meta llama3-8b","year":"2025"},{"key":"ref24","volume-title":"Meta llama3-70b","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/access.2025.3546700"},{"key":"ref26","author":"Ferrag","year":"2023","journal-title":"Securefalcon: The next cyber reasoning system for cyber security"},{"key":"ref27","author":"Fang","year":"2024","journal-title":"Llm agents can autonomously exploit one-day vulnerabilities"},{"key":"ref28","author":"Li","year":"2024","journal-title":"Llm-assisted static analysis for detecting security vulnerabilities"},{"key":"ref29","author":"Guo","year":"2023","journal-title":"Owl: A large language model for it operations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CNS59707.2023.10288677"},{"key":"ref31","article-title":"Ctikg: Llm-powered knowledge graph construction from cyber threat intelligence","volume-title":"First Conference on Language Modeling","author":"Huang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref33","author":"Hendrycks","year":"2020","journal-title":"Measuring massive multitask language understanding"},{"key":"ref34","article-title":"Kola: Carefully benchmarking world knowledge of large language models","volume-title":"ICLR","author":"Yu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/csr61664.2024.10679494"},{"key":"ref36","author":"Miao","year":"2023","journal-title":"An empirical study of netops capability of pre-trained large language models"},{"key":"ref37","author":"Liu","year":"2023","journal-title":"Opseval: A comprehensive task-oriented aiops benchmark for large language models"},{"key":"ref38","article-title":"Common weakness enumeration","author":"Christey","year":"2013","journal-title":"Mitre Corporation"},{"key":"ref39","article-title":"Common attack pattern enumerations and classifications","year":"2024"},{"key":"ref40","article-title":"Cybersecurity and infrastructure security agency","year":"2024"},{"key":"ref41","volume-title":"Threat intelligence standards","year":"2025"},{"key":"ref42","volume-title":"European union, gdpr","year":"2025"},{"key":"ref44","volume-title":"Mitre mitigations"},{"key":"ref45","volume-title":"Mitre attack"},{"key":"ref46","article-title":"Cvss library with interactive calculator for python","year":"2023"}],"event":{"name":"2025 Annual Computer Security Applications Conference Workshops (ACSAC Workshops)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,9]]}},"container-title":["2025 Annual Computer Security Applications Conference Workshops (ACSAC Workshops)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11417955\/11417996\/11418063.pdf?arnumber=11418063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T05:34:27Z","timestamp":1773120867000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11418063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/acsacw69556.2025.00072","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}