多智能体协作攻击:通过辩论研究大型语言模型协作中的对抗性攻击
MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate
AI总结:
本研究通过辩论场景,探究对抗性攻击对多大型语言模型协作网络的影响,提出评估指标,发现说服能力是关键,并探索推理时增强论点及提示缓解的防御策略。
摘要:
大型语言模型(LLMs)在单独工作时已在当前基准测试中展现出卓越的结果。其能力的提升,以及参数规模和推理时间的减少,促进了这些模型作为智能体的使用,使得多个模型之间能够进行交互以执行复杂任务。这种协作提供了多项优势,包括使用专用模型(例如编码)、通过多次计算提高置信度,以及增强发散性思维,从而产生更多样化的输出。因此,语言模型的协作使用在未来几年预计将显著增长。在这项工作中,我们评估了一个通过辩论进行协作的模型网络在对抗者影响下的行为。我们引入了相关指标来评估对抗者的有效性,重点关注系统准确性和模型一致性。我们的研究结果强调了模型说服能力在影响他人方面的重要性。此外,我们探索了推理时的方法来生成更有说服力的论点,并评估了基于提示的缓解措施作为防御策略的潜力。
英文摘要:
Large Language Models (LLMs) have shown exceptional results on current benchmarks when working individually. The advancement in their capabilities, along with a reduction in parameter size and inference times, has facilitated the use of these models as agents, enabling interactions among multiple models to execute complex tasks. Such collaborations offer several advantages, including the use of specialized models (e.g. coding), improved confidence through multiple computations, and enhanced divergent thinking, leading to more diverse outputs. Thus, the collaborative use of language models is expected to grow significantly in the coming years. In this work, we evaluate the behavior of a network of models collaborating through debate under the influence of an adversary. We introduce pertinent metrics to assess the adversary's effectiveness, focusing on system accuracy and model agreement. Our findings highlight the importance of a model's persuasive ability in influencing others. Additionally, we explore inference-time methods to generate more compelling arguments and evaluate the potential of prompt-based mitigation as a defensive strategy.
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。