评估 LLM 被滥用于生成个性化虚假信息的脆弱性
Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation Generation
AI总结：
该研究评估开源与闭源 LLM 生成个性化英文虚假新闻的脆弱性，发现个性化会降低安全过滤器激活并形成越狱效果。
摘要：
近期大型语言模型（LLM）能够生成人类无法与人类撰写文本区分的高质量内容，这引发了许多关于其被滥用的担忧。先前研究表明，LLM 可被有效滥用于按照预定义叙事生成虚假新闻文章。它们在多个方面生成个性化内容的能力也已得到评估，且大多被认为可用。然而，LLM 的个性化能力与虚假信息能力的结合尚未得到全面研究。如果 LLM 具备集成安全过滤器，这种危险的组合应当触发这些过滤器。本研究通过评估近期开源和闭源 LLM 的脆弱性，以及它们生成英文个性化虚假新闻文章的意愿，填补了这一空白。我们进一步探究 LLM 能否可靠地对个性化质量进行元评估，以及个性化是否会影响生成文本的可检测性。结果表明，需要更强的安全过滤器和免责声明，因为在大多数受评估 LLM 中，这些机制未能正常发挥作用。此外，研究揭示个性化实际上会降低安全过滤器的激活率，从而有效充当越狱手段。LLM 开发者和服务提供商必须紧急处理此类行为。
英文摘要：
The capabilities of recent large language models (LLMs) to generate high-quality content indistinguishable by humans from human-written texts raises many concerns regarding their misuse. Previous research has shown that LLMs can be effectively misused for generating disinformation news articles following predefined narratives. Their capabilities to generate personalized (in various aspects) content have also been evaluated and mostly found usable. However, a combination of personalization and disinformation abilities of LLMs has not been comprehensively studied yet. Such a dangerous combination should trigger integrated safety filters of the LLMs, if there are some. This study fills this gap by evaluating vulnerabilities of recent open and closed LLMs, and their willingness to generate personalized disinformation news articles in English. We further explore whether the LLMs can reliably meta-evaluate the personalization quality and whether the personalization affects the generated-texts detectability. Our results demonstrate the need for stronger safety-filters and disclaimers, as those are not properly functioning in most of the evaluated LLMs. Additionally, our study revealed that the personalization actually reduces the safety-filter activations; thus effectively functioning as a jailbreak. Such behavior must be urgently addressed by LLM developers and service providers.
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。
