面向优化的大语言模型黑盒越狱攻击研究综述OA

Large Language Models(LLMs)have demonstrated remarkable capabilities in Natural Language Processing(NLP).However,their security vulnerabilities,particularly jailbreak attacks,pose a critical chal-lenge.These attacks circumvent safety alignment mechanisms through carefully crafted adversarial prompts,revealing the limitations of alignment techniques like Reinforcement Learning from Human Feedback(RLHF).Template-based or manually crafted jailbreak methods typically exhibit low success rates and poor generalization,and they rapidly become obsolete as LLM safety mechanisms evolve.In contrast,optimization-based methods automatically generate adversarial prompts,leading to higher success rates and better stealthiness that effectively bypass common detection mechanisms.To overcome the limitations of white-box attacks,such as their reliance on gradients and limited transferability,the review investigates the black-box optimization paradigm and presents the first systematic taxonomy of jailbreak methods:Genetic Al-gorithm(GA)-based,Reinforcement Learning(RL)-based,Fuzzing-based,and LLM-based Adversarial Optimization.We delve into the core mechanisms,technical strengths,and limitations of each category.The primary contribution of this survey is proposing a novel taxonomy that critically examines existing defenses'deficiencies in real-time performance,generalizability,and attack-defense balance.It further advocates for dy-namic defense architectures and standardized benchmarks,thereby providing a theoretical foundation and prac-tical guidance for balancing the security and performance of LLMs in adversarial settings.