參考文獻
[1] G. Deng, Y. Liu, V. Mayoral-Vilches, P. Liu, Y. Li, Y. Xu, T. Zhang, Y. Liu, M. Pinzger, and S. Rass, “PentestGPT: Evaluating and harnessing large language models for automated penetration testing,” in Proc. USENIX Security 2024, Aug. 2024, pp. 847–864.
[2] S. S. Roy, P. Thota, K. V. Naragam, and S. Nilizadeh, “From chatbots to phishbots?: Phishing scam generation in commercial large language models,” in Proc. IEEE S&P 2024, May 2024, pp. 36–54.
[3] R. Meng, M. Mirchev, M. Böhme, and A. Roychoudhury, “Large language model guided protocol fuzzing,” in Proc. NDSS Symposium 2024, Feb. 2024.
[4] Y. Lyu, Y. Xie, P. Chen, and H. Chen, “Prompt fuzzing for fuzz driver generation,” in Proc. ACM CCS 2024, Oct. 2024, pp. 3793–3807.
[5] M. Nazzal, I. Khalil, A. Khreishah, and N. Phan, “Promsec: Prompt optimization for secure generation of functional source code with large language models (LLMs),” in Proc. ACM CCS 2024, Oct. 2024, pp. 2266–2280.
[6] H. Liang, X. Li, D. Xiao, J. Liu, Y. Zhou, A. Wang, and J. Li, “Generative pre-trained transformer-based reinforcement learning for testing web application firewalls,” IEEE Transactions on Dependable and Secure Computing, vol. 21, no. 1, pp. 309–324, Jan.-Feb. 2024.
[7] Z. Yu, M. Wen, X. Guo, and H. Jin, “Maltracker: A fine-grained npm malware tracker copiloted by llm-enhanced dataset,” in Proc. ACM ISSTA 2024, Sep. 2024, pp. 1759–1771.
[8] J. Jeong, I. Baek, B. Bang, J. Lee, U. Song, and S. B. Kim, “Fall: Prior failure detection in large scale system based on language model,” IEEE Transactions on Dependable and Secure Computing, vol. 22, no. 1, pp. 279–291, Jan.-Feb. 2025.
[9] J. Lin and D. Mohaisen, “From large to Mammoth: A comparative evaluation of large language models in vulnerability detection,” in Proc. NDSS Symposium 2025, Jan. 2025.
[10] DARPA, “AI Cyber Challenge Final Results,” Aug. 2025. [Online]. Available: https://www.darpa.mil/news/2025/aixcc-results
[11] J.-Y. Yao, K.-P. Ning, Z.-H. Liu, M.-N. Ning, Y.-Y. Liu, and L. Yuan, “LLM lies: Hallucinations are not bugs, but features as adversarial examples,” arXiv preprint arXiv:2310.01469, Aug. 2024.
[12] R. Schuster, C. Song, E. Tromer, and V. Shmatikov, “You autocomplete me: Poisoning vulnerabilities in neural code completion,” in Proc. USENIX Security 2021, Aug. 2021, pp. 1559–1575.
[13] H. Yu, K. Yang, T. Zhang, Y.-Y. Tsai, T.-Y. Ho, and Y. Jin, “Cloudleak: Large-scale deep learning models stealing through adversarial examples,” in Proc. NDSS Symposium 2020, Feb. 2020.
[14] W. Kuang, B. Qian, Z. Li, D. Chen, D. Gao, X. Pan, Y. Xie, Y. Li, B. Ding, and J. Zhou, “Federatedscope-llm: A comprehensive package for fine-tuning large language models in federated learning,” in Proc. ACM KDD 2024, Aug. 2024, pp. 5260–5271.
[15] R. Zhang, S. S. Hussain, P. Neekhara, and F. Koushanfar, “REMARK-LLM: A robust and efficient watermarking framework for generative large language models,” in Proc. USENIX Security 2024, Aug. 2024, pp. 1813–1830.
[16] 台灣資安院, 「AI 模型安全檢測平台簡介」, 2024. [Online]. Available: https://www.tw-nics.tw
[17] L. Ahmad, S. Agarwal, M. Lampe, and P. Mishkin, “OpenAI’s approach to external red teaming for AI models and systems,” arXiv preprint arXiv:2503.16431, Jan. 2025.