最安全者生存：通过交错多目标进化实现安全的提示优化
Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution
AI总结：
针对LLM提示优化重性能轻安全的问题，提出多目标进化框架SoS，结合多种突变策略加速高维离散搜索，在保持低计算开销的同时显著提升模型性能与安全性。
摘要：
大型语言模型（LLMs）展现出了卓越的能力；然而，其提示的优化在历史上一直优先考虑性能指标，而牺牲了关键的安全性和安全性考量。为了克服这一缺陷，我们引入了“Survival of the Safest”（SoS），这是一种创新的多目标提示优化框架，能够同时提升LLMs的性能和安全性。SoS采用交错的多目标进化策略，结合语义、反馈和交叉突变，以有效地遍历提示空间。与计算需求高的Pareto前沿方法不同，SoS提供了一种可扩展的解决方案，能够加速复杂、高维离散搜索空间中的优化过程，同时保持较低的计算需求。我们的方法支持目标的灵活加权，并生成一个优化候选池，使用户能够选择最符合其特定性能和安全需求的提示。在多个基准数据集上的实验评估证实，与单目标方法相比，SoS在提供高性能和显著增强安全性方面具有有效性。这一进展标志着在跨各种工业应用部署兼具高性能和安全性的LLM系统方面迈出了重要一步。
英文摘要：
Large language models (LLMs) have demonstrated remarkable capabilities; however, the optimization of their prompts has historically prioritized performance metrics at the expense of crucial safety and security considerations. To overcome this shortcoming, we introduce "Survival of the Safest" (SoS), an innovative multi-objective prompt optimization framework that enhances both performance and security in LLMs simultaneously. SoS utilizes an interleaved multi-objective evolution strategy, integrating semantic, feedback, and crossover mutations to effectively traverse the prompt landscape. Differing from the computationally demanding Pareto front methods, SoS provides a scalable solution that expedites optimization in complex, high-dimensional discrete search spaces while keeping computational demands low. Our approach accommodates flexible weighting of objectives and generates a pool of optimized candidates, empowering users to select prompts that optimally meet their specific performance and security needs. Experimental evaluations across diverse benchmark datasets affirm SoS's efficacy in delivering high performance and notably enhancing safety and security compared to single-objective methods. This advancement marks a significant stride towards the deployment of LLM systems that are both high-performing and secure across varied industrial applications
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
