穿行阴影：揭示现代 AI 内容检测器面临的有效扰动
Navigating the Shadows: Unveiling Effective Disturbances for Modern AI Content Detectors
AI总结：
该研究面向非正式与专业写作场景，系统评估现代 AI 文本检测器的开箱即用性能，并用 12 种黑盒扰动及对抗学习考察其鲁棒性与数据增强效果。
摘要：
随着 ChatGPT 的发布，大型语言模型（LLM）吸引了全球关注。在文章写作领域，LLM 已得到广泛应用，也引发了与知识产权保护、个人隐私和学术诚信有关的担忧。为此，AI 文本检测应运而生，用于区分人类生成内容与机器生成内容。然而，近期研究表明，这些检测系统往往缺乏鲁棒性，难以有效区分经过扰动的文本。目前，针对现实应用中检测性能的系统性评估仍然不足，对扰动技术和检测器鲁棒性也缺乏全面考察。为弥补这一差距，本研究在非正式写作和专业写作两类场景中模拟现实情境，考察当前检测器的开箱即用性能。此外，我们构建了 12 种黑盒文本扰动方法，以在不同扰动粒度上评估当前检测模型的鲁棒性。进一步地，我们通过对抗学习实验，研究扰动数据增强对 AI 文本检测器鲁棒性的影响。我们已在 https://github.com/zhouying20/ai-text-detector-evaluation 发布代码和数据。
英文摘要：
With the launch of ChatGPT, large language models (LLMs) have attracted global attention. In the realm of article writing, LLMs have witnessed extensive utilization, giving rise to concerns related to intellectual property protection, personal privacy, and academic integrity. In response, AI-text detection has emerged to distinguish between human and machine-generated content. However, recent research indicates that these detection systems often lack robustness and struggle to effectively differentiate perturbed texts. Currently, there is a lack of systematic evaluations regarding detection performance in real-world applications, and a comprehensive examination of perturbation techniques and detector robustness is also absent. To bridge this gap, our work simulates real-world scenarios in both informal and professional writing, exploring the out-of-the-box performance of current detectors. Additionally, we have constructed 12 black-box text perturbation methods to assess the robustness of current detection models across various perturbation granularities. Furthermore, through adversarial learning experiments, we investigate the impact of perturbation data augmentation on the robustness of AI-text detectors. We have released our code and data at https://github.com/zhouying20/ai-text-detector-evaluation.
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。
