盲目说谎：绕过ChatGPT的安全防护生成难以检测的虚假信息声明
Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims
AI总结：
本研究通过简单提示技术绕过ChatGPT（GPT-3.5）的安全防护，生成乌克兰战争相关的虚假信息声明，发现其内容逼真且人类和现有检测工具均难以可靠识别。
摘要：
随着大语言模型能力日益精进，其被滥用于协同虚假信息活动的问题引发越来越多的担忧。本研究探究了搭载GPT-3.5的ChatGPT生成关于乌克兰战争的短篇虚假信息声明的能力，涵盖通用场景以及超出GPT-3.5知识截断时间的特定事件场景。与已有研究不同，我们未在提示词中加入人工撰写的虚假信息叙事来提供给模型，因此生成的短篇声明是模型基于既有世界知识和对极简提示的推理产生的幻觉。通过一种简单直接的提示工程技术，我们能够绕过模型的安全防护，生成大量短篇声明。我们将这些声明与来自ClaimReview（虚假信息核查标注库）的人工撰写的乌克兰战争虚假声明进行对比，重点分析二者在语言特征上的差异。我们还评估了人类读者以及最先进的作者身份检测工具能否区分AI生成的内容。研究结果表明，ChatGPT能够生成逼真的、针对特定目标的虚假信息声明，即便针对知识截断时间之后的特定事件也能生成，且人类和现有自动化工具都无法可靠区分这些AI生成内容。
英文摘要：
As Large Language Models become more proficient, their misuse in coordinated disinformation campaigns is a growing concern. This study explores the capability of ChatGPT with GPT-3.5 to generate short-form disinformation claims about the war in Ukraine, both in general and on a specific event, which is beyond the GPT-3.5 knowledge cutoff. Unlike prior work, we do not provide the model with human-written disinformation narratives by including them in the prompt. Thus the generated short claims are hallucinations based on prior world knowledge and inference from the minimal prompt. With a straightforward prompting technique, we are able to bypass model safeguards and generate numerous short claims. We compare those against human-authored false claims on the war in Ukraine from ClaimReview, specifically with respect to differences in their linguistic properties. We also evaluate whether AI authorship can be differentiated by human readers or state-of-the-art authorship detection tools. Thus, we demonstrate that ChatGPT can produce realistic, target-specific disinformation claims, even on a specific post-cutoff event, and that they cannot be reliably distinguished by humans or existing automated tools.
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。
