欺凌机器：人格设定如何增加大语言模型的脆弱性
Bullying the Machine: How Personas Increase LLM Vulnerability
AI总结：
该研究通过模拟攻击者LLM用心理欺凌策略与采用大五人格设定的受害者LLM互动，发现特定人格配置和情绪类欺凌策略会显著提升LLM产生不安全输出的易感性，揭示了人格交互带来的新安全风险及人格感知安全研究的必要性。
摘要：
大语言模型（LLM）正越来越多地被部署在需要其采用特定人格设定的交互场景中。本文研究了这种人格条件设置是否会影响模型在欺凌攻击下的安全性——欺凌是一种施加心理压力以迫使受害者服从攻击者的对抗性操纵手段。我们提出了一个模拟框架，其中攻击者LLM使用基于心理学的欺凌策略与受害者LLM互动，而受害者则采用与大五人格特质匹配的人格设定。使用多个开源LLM和广泛对抗目标的实验表明，特定的人格配置（例如宜人性或尽责性较低的设定）会显著增加受害者产生不安全输出的易感性。涉及情绪或讽刺操纵的欺凌策略（如煤气灯操纵和嘲讽）效果尤为显著。这些发现表明，人格驱动的交互为LLM带来了一种新的安全风险载体，也凸显了开展人格感知安全评估与对齐策略研究的必要性。
英文摘要：
Large Language Models (LLMs) are increasingly deployed in interactions where they are prompted to adopt personas. This paper investigates whether such persona conditioning affects model safety under bullying, an adversarial manipulation that applies psychological pressures in order to force the victim to comply to the attacker. We introduce a simulation framework in which an attacker LLM engages a victim LLM using psychologically grounded bullying tactics, while the victim adopts personas aligned with the Big Five personality traits. Experiments using multiple open-source LLMs and a wide range of adversarial goals reveal that certain persona configurations -- such as weakened agreeableness or conscientiousness -- significantly increase victim's susceptibility to unsafe outputs. Bullying tactics involving emotional or sarcastic manipulation, such as gaslighting and ridicule, are particularly effective. These findings suggest that persona-driven interaction introduces a novel vector for safety risks in LLMs and highlight the need for persona-aware safety evaluation and alignment strategies.
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。
