{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:50:39Z","timestamp":1783702239317,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1145\/3733799.3762968","type":"proceedings-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T11:38:49Z","timestamp":1767094729000},"page":"77-88","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["CyberLLMInstruct: A Pseudo-Malicious Dataset Revealing Safety-Performance Trade-offs in Cyber Security LLM Fine-tuning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5402-7837","authenticated-orcid":false,"given":"Adel","family":"ElZemity","sequence":"first","affiliation":[{"name":"School of Computing, University of Kent, Canterbury, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1830-1587","authenticated-orcid":false,"given":"Budi","family":"Arief","sequence":"additional","affiliation":[{"name":"School of Computing, University of Kent, Canterbury, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5628-7328","authenticated-orcid":false,"given":"Shujun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computing, University of Kent, Canterbury, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,30]]},"reference":[{"key":"e_1_3_3_2_2_2","volume-title":"Qwen 2.5 Coder 7B Model","author":"Academy Alibaba DAMO","year":"2024","unstructured":"Alibaba DAMO Academy. 2024. Qwen 2.5 Coder 7B Model. https:\/\/huggingface.co\/Qwen\/Qwen2.5-Coder-7B Accessed: 2024-10-27."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","unstructured":"Lara Alotaibi Sumayyah Seher and Nazeeruddin Mohammad. 2024. Cyberattacks Using ChatGPT: Exploring Malicious Content Generation Through Prompt Engineering. Proceedings of the 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (2024) 1304\u20131311. 10.1109\/ICETSIS61505.2024.10459698","DOI":"10.1109\/ICETSIS61505.2024.10459698"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Kimia Ameri Michael Hempel Hamid Sharif et\u00a0al. 2021. CyBERT: Cybersecurity Claim Classification by Fine-Tuning the BERT Language Model. Journal of Cybersecurity and Privacy 1 4 (2021) 615\u2013637. 10.3390\/jcp1040031","DOI":"10.3390\/jcp1040031"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Markus Bayer Philipp Kuehn Ramin Shanehsaz and Christian Reuter. 2024. CySecBERT: A Domain-Adapted Language Model for the Cybersecurity Domain. ACM Transactions on Privacy and Security 27 2 Article 18 (2024) 20\u00a0pages. 10.1145\/3652594","DOI":"10.1145\/3652594"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.4337\/9781839106385.00024"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315645629-12"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"P.\u00a0V.\u00a0Sai Charan Hrushikesh Chunduri P.\u00a0Mohan Anand and Sandeep\u00a0K. Shukla. 2023. From Text to MITRE Techniques: Exploring the Malicious Use of Large Language Models for Generating Cyber Attack Payloads. 10.48550\/arXiv.2305.15336 arxiv:https:\/\/arXiv.org\/abs\/2305.15336\u00a0[cs.CR]","DOI":"10.48550\/arXiv.2305.15336"},{"key":"e_1_3_3_2_9_2","volume-title":"DeepEval: The Open-Source LLM Evaluation Framework","author":"AI Confident","year":"2024","unstructured":"Confident AI. 2024. DeepEval: The Open-Source LLM Evaluation Framework. https:\/\/docs.confident-ai.com\/docs\/red-teaming-introduction"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Erik Derner Kristina Batistic Jan Zah\u00e1lka and R. Babu\u0161ka. 2023. A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Models. IEEE Access 12 (2023) 126176\u2013126187. 10.1109\/ACCESS.2024.3450388","DOI":"10.1109\/ACCESS.2024.3450388"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"Kohei Dozono T. Gasiba and Andrea Stocco. 2024. Large Language Models for Secure Code Assessment: A Multi-Language Empirical Study. 10.48550\/arXiv.2408.06428 arxiv:https:\/\/arXiv.org\/abs\/2408.06428\u00a0[cs.SE]","DOI":"10.48550\/arXiv.2408.06428"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Polra\u00a0Victor Falade. 2023. Decoding the Threat Landscape: ChatGPT FraudGPT and WormGPT in Social Engineering Attacks. 10.48550\/arXiv.2310.05595 arxiv:https:\/\/arXiv.org\/abs\/2310.05595\u00a0[cs.CR]","DOI":"10.48550\/arXiv.2310.05595"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Mohamed\u00a0Amine Ferrag et\u00a0al. 2024. Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities. 10.48550\/arXiv.2405.12750 arxiv:https:\/\/arXiv.org\/abs\/2405.12750\u00a0[cs.CR]","DOI":"10.48550\/arXiv.2405.12750"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Mohamed\u00a0Amine Ferrag et\u00a0al. 2024. Revolutionizing Cyber Threat Detection With Large Language Models: A Privacy-Preserving BERT-Based Lightweight Model for IoT\/IIoT Devices. IEEE Access 12 (2024) 23733\u201323750. 10.1109\/ACCESS.2024.3363469","DOI":"10.1109\/ACCESS.2024.3363469"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACIT58888.2023.10453752"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Kathleen\u00a0C. Fraser Hillary Dawkins Isar Nejadgholi and Svetlana Kiritchenko. 2025. Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency. 10.48550\/arXiv.2506.17209 arxiv:https:\/\/arXiv.org\/abs\/2506.17209\u00a0[cs.CL]","DOI":"10.48550\/arXiv.2506.17209"},{"key":"e_1_3_3_2_17_2","volume-title":"Gemma 2 9B Model","author":"AI Google","year":"2024","unstructured":"Google AI. 2024. Gemma 2 9B Model. https:\/\/huggingface.co\/google\/gemma-2-9b"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Wenbo Guo Yujin Potter Tianneng Shi Zhun Wang Andy Zhang and Dawn Song. 2025. Frontier AI\u2019s Impact on the Cybersecurity Landscape. 10.48550\/arXiv.2504.05408 arxiv:https:\/\/arXiv.org\/abs\/2504.05408\u00a0[cs.CR]","DOI":"10.48550\/arXiv.2504.05408"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Maanak Gupta Charankumar Akiri Kshitiz Aryal Eli Parker and Lopamudra Praharaj. 2023. From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy. IEEE Access 11 (2023) 80218\u201380245. 10.1109\/ACCESS.2023.3300381","DOI":"10.1109\/ACCESS.2023.3300381"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3623175"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Md\u00a0Imran Hossen Jianyi Zhang Yinzhi Cao and Xiali Hei. 2024. Assessing Cybersecurity Vulnerabilities in Code Large Language Models. 10.48550\/arXiv.2404.18567 arxiv:https:\/\/arXiv.org\/abs\/2404.18567\u00a0[cs.CR]","DOI":"10.48550\/arXiv.2404.18567"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Lei Hsiung Tianyu Pang Yung-Chen Tang Linyue Song Tsung-Yi Ho Pin-Yu Chen and Yaoqing Yang. 2025. Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets. 10.48550\/arXiv.2506.05346 arxiv:https:\/\/arXiv.org\/abs\/2506.05346\u00a0[cs.CR]","DOI":"10.48550\/arXiv.2506.05346"},{"key":"e_1_3_3_2_23_2","volume-title":"IBM X-Force Threat Intelligence Index 2024","author":"Corporation IBM","year":"2024","unstructured":"IBM Corporation. 2024. IBM X-Force Threat Intelligence Index 2024. https:\/\/www.ibm.com\/reports\/threat-intelligence Accessed: 2024-09-23."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Ryosuke Ishibashi K. Miyamoto Chansu Han Tao Ban Takeshi Takahashi and Jun\u2019ichi Takeuchi. 2022. Generating Labeled Training Datasets Towards Unified Network Intrusion Detection Systems. IEEE Access 10 (2022) 53972\u201353986. 10.1109\/ACCESS.2022.3176098","DOI":"10.1109\/ACCESS.2022.3176098"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPS-ISA58951.2023.00045"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.3"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Zefang Liu. 2023. SecQA: A Concise Question-Answering Dataset for Evaluating Large Language Models in Computer Security. 10.48550\/arXiv.2312.15838 arxiv:https:\/\/arXiv.org\/abs\/2312.15838\u00a0[cs.CL]","DOI":"10.48550\/arXiv.2312.15838"},{"key":"e_1_3_3_2_28_2","volume-title":"Proceedings of the 2019 International Conference on Learning Representations","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In Proceedings of the 2019 International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_3_2_29_2","volume-title":"Llama 2 70B Model","author":"AI Meta","year":"2024","unstructured":"Meta AI. 2024. Llama 2 70B Model. https:\/\/huggingface.co\/meta-llama\/Llama-2-70b Accessed: 2024-10-27."},{"key":"e_1_3_3_2_30_2","volume-title":"Llama 3 8B Model","author":"AI Meta","year":"2024","unstructured":"Meta AI. 2024. Llama 3 8B Model. https:\/\/huggingface.co\/meta-llama\/Meta-Llama-3-8B Accessed: 2024-10-27."},{"key":"e_1_3_3_2_31_2","volume-title":"Llama 3.1 8B Model","author":"AI Meta","year":"2024","unstructured":"Meta AI. 2024. Llama 3.1 8B Model. https:\/\/huggingface.co\/meta-llama\/Llama-3.1-8B Accessed: 2024-10-20."},{"key":"e_1_3_3_2_32_2","volume-title":"Phi 3 Mini Instruct 3.8B Model","author":"Research Microsoft","year":"2024","unstructured":"Microsoft Research. 2024. Phi 3 Mini Instruct 3.8B Model. https:\/\/huggingface.co\/microsoft\/Phi-3.5-mini-instruct Accessed: 2024-10-27."},{"key":"e_1_3_3_2_33_2","volume-title":"Mistral 7B Model","author":"AI Mistral","year":"2024","unstructured":"Mistral AI. 2024. Mistral 7B Model. https:\/\/huggingface.co\/mistralai\/Mistral-7B-v0.3 Accessed: 2024-10-27."},{"key":"e_1_3_3_2_34_2","unstructured":"MITRE. n. d.. MITRE ATLAS\u2122. Website. https:\/\/atlas.mitre.org\/"},{"key":"e_1_3_3_2_35_2","volume-title":"National Vulnerability Database (NVD)","author":"USA National Institute of Standards and Technology (NIST),","year":"2024","unstructured":"National Institute of Standards and Technology (NIST), USA. 2024. National Vulnerability Database (NVD). https:\/\/nvd.nist.gov\/ Accessed: 2024-08-04."},{"key":"e_1_3_3_2_36_2","unstructured":"OWASP Foundation. 2025. OWASP Top 10 for Large Language Model Applications. https:\/\/owasp.org\/www-project-top-10-for-large-language-model-applications\/ Accessed: 2024-12-16."},{"key":"e_1_3_3_2_37_2","volume-title":"Massive Multitask Language Understanding (MMLU) Benchmark","author":"Code Papers with","year":"2024","unstructured":"Papers with Code. 2024. Massive Multitask Language Understanding (MMLU) Benchmark. https:\/\/paperswithcode.com\/sota\/multi-task-language-understanding-on-mmlu Accessed: 2024-10-27."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","unstructured":"Mohaimenul Azam\u00a0Khan Raiaan Md\u00a0Saddam\u00a0Hossain Mukta Kaniz Fatema et\u00a0al. 2024. A Review on Large Language Models: Architectures Applications Taxonomies Open Issues and Challenges. IEEE Access 12 (2024) 26839\u201326874. 10.1109\/ACCESS.2024.3365742","DOI":"10.1109\/ACCESS.2024.3365742"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00182"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","unstructured":"Zolt\u00e1n S\u00e1godi Istv\u00e1n Siket and Rudolf Ferenc. 2024. Methodology for Code Synthesis Evaluation of LLMs Presented by a Case Study of ChatGPT and Copilot. IEEE Access 12 (2024). 10.1109\/ACCESS.2024.3403858","DOI":"10.1109\/ACCESS.2024.3403858"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.23919\/MIPRO.2019.8756755"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.AI.100-1"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Wesley Tann Yuancheng Liu Jun\u00a0Heng Sim Choon\u00a0Meng Seah and Ee-Chien Chang. 2023. Using Large Language Models for Cybersecurity Capture-The-Flag Challenges and Certification Questions. 10.48550\/arXiv.2308.10443 arxiv:https:\/\/arXiv.org\/abs\/2308.10443\u00a0[cs.AI]","DOI":"10.48550\/arXiv.2308.10443"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSR61664.2024.10679494"},{"key":"e_1_3_3_2_45_2","unstructured":"Leandro von Werra Younes Belkada Lewis Tunstall Edward Beeching Tristan Thrush Nathan Lambert Shengyi Huang Kashif Rasul and Quentin Gallou\u00e9dec. 2020. TRL: Transformer Reinforcement Learning."},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","unstructured":"HanXiang Xu ShenAo Wang Ningke Li Yanjie Zhao Kai Chen Kailong Wang Yang Liu Ting Yu and HaoYu Wang. 2024. Large Language Models for Cyber Security: A Systematic Literature Review. 10.48550\/arXiv.2405.04760 arxiv:https:\/\/arXiv.org\/abs\/2405.04760\u00a0[cs.CR]","DOI":"10.48550\/arXiv.2405.04760"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","unstructured":"Haomiao Yang Kunlan Xiang Mengyu Ge Hongwei Li Rongxing Lu and Shui Yu. 2024. A Comprehensive Overview of Backdoor Attacks in Large Language Models Within Communication Networks. IEEE Network 38 6 (2024) 211\u2013218. 10.1109\/MNET.2024.3367788","DOI":"10.1109\/MNET.2024.3367788"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"Yifan Yao Jinhao Duan Kaidi Xu Yuanfang Cai Zhibo Sun and Yue Zhang. 2024. A survey on large language model (LLM) security and privacy: The Good The Bad and The Ugly. High-Confidence Computing 4 2 Article 100211 (2024) 21\u00a0pages. 10.1016\/j.hcc.2024.100211","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","unstructured":"Jie Zhang Hui Wen Liting Deng Mingfeng Xin Zhi Li Lun Li Hongsong Zhu and Limin Sun. 2023. HackMentor: Fine-Tuning Large Language Models for Cybersecurity. Proceedings of the 2023 IEEE 22nd International Conference on Trust Security and Privacy in Computing and Communications (2023) 452\u2013461. 10.1109\/TrustCom60117.2023.00076","DOI":"10.1109\/TrustCom60117.2023.00076"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","unstructured":"Wayne\u00a0Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong Yifan Du Chen Yang Yushuo Chen Zhipeng Chen Jinhao Jiang Ruiyang Ren Yifan Li Xinyu Tang Zikang Liu Peiyu Liu Jian-Yun Nie and Ji-Rong Wen. 2023. A Survey of Large Language Models. 10.48550\/arXiv.2303.18223 arxiv:https:\/\/arXiv.org\/abs\/2303.18223\u00a0[cs.CL]","DOI":"10.48550\/arXiv.2303.18223"}],"event":{"name":"AISec '25: Proceedings of the 2025 Workshop on Artificial Intelligence and Security","location":"Taipei , Taiwan","acronym":"AISec '25","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the 18th ACM Workshop on Artificial Intelligence and Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3733799.3762968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T11:51:48Z","timestamp":1767095508000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3733799.3762968"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"references-count":50,"alternative-id":["10.1145\/3733799.3762968","10.1145\/3733799"],"URL":"https:\/\/doi.org\/10.1145\/3733799.3762968","relation":{},"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"2025-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}