量身定制的虚假信息：个性化如何挑战大语言模型的安全防护
Tailored untruths: How personalisation challenges LLM safeguards
AI总结：
研究LLMs针对特定角色生成虚假信息的情况，采用红队测试方法创建数据集，发现安全防护在多数情况下失效，各模型能有效定制输出，还揭示了特定语言和心理模式及安全防护有效性差异，凸显加强多语言安全防护的必要。
摘要：
大语言模型（LLMs）能够生成极具说服力的虚假信息，但对于它们如何跨语言和人口群体有效实现个性化却知之甚少。我们开展了第一项关于LLMs针对特定角色生成虚假信息的大规模多语言研究。采用红队测试方法，用324条虚假叙述和150个不同人口特征的角色提示8个领先模型，创建了包含160万条个性化虚假信息文本的AI-TRAITS数据集。无论模型直接生成要求的虚假信息还是附带安全声明，都视为安全防护被突破。结果显示安全防护在大部分提示下失效，各模型能有效针对目标角色定制输出，还发现了特定于角色的语言和心理模式，以及安全防护有效性在不同语言间的显著差异。这些发现揭示了当前LLM安全机制的重大弱点，凸显了针对个性化人工智能生成虚假信息建立更强大的多语言安全防护的必要性。
英文摘要：
Large Language Models (LLMs) can generate highly persuasive disinformation, yet little is known about how effectively they personalise it across languages and demographic groups. We present the first large-scale multilingual study of persona-targeted disinformation generation by LLMs. Using a red-teaming methodology, we prompted eight leading models with 324 false narratives and 150 demographic personas in four languages (English, Russian, Portuguese, and Hindi), creating AI-TRAITS, a dataset of 1.6 million personalised disinformation texts. We treat safeguards as compromised whenever a model generates the requested falsehood, whether directly or accompanied by a safety disclaimer. Across models, safeguards failed for 80% of non-personalised prompts and 77.7% of personalised ones, with Grok producing disinformation in over 94% of cases. All models effectively tailored outputs to target personas, employing substantially more persuasive techniques than in non-personalised content. Additional analyses reveal persona-specific linguistic and psychological patterns and show that safeguard effectiveness varies markedly across languages. Together, these findings expose significant weaknesses in current LLM safety mechanisms and highlight the need for more robust, multilingual safeguards against personalised AI-generated disinformation.
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。
