ALISON：快速高效的文体计量学作者身份混淆方法
ALISON: Fast and Effective Stylometric Authorship Obfuscation
AI总结：
针对现有作者身份混淆方法速度慢、实用性不足的问题，提出ALISON方法，在大幅提升混淆速度的同时取得更优效果，还具备可解释性，可保护ChatGPT生成文本的作者隐私。
摘要：
作者身份归属（Authorship Attribution，AA）与作者身份混淆（Authorship Obfuscation，AO）是隐私研究中重要性日益提升的一对对立任务。现代AA技术利用作者一致的写作风格，通过AA分类器将文本与其作者进行匹配。AO是对应的对抗性任务，目标是在保留文本语义的前提下修改文本，使AA模型无法正确推断其作者。为应对前沿（state-of-the-art，SOTA）AA方法带来的隐私风险，已有新的AO方法被提出，但这类方法的训练和混淆速度极慢，往往需要数小时，因此大多仍不具备实用性。针对这一挑战，我们提出了一种实用的AO方法ALISON，它具备以下特点：（1）大幅缩短训练/混淆时间，混淆速度比SOTA AO方法快10倍以上；（2）在两个基准数据集上攻击三种基于transformer的AA方法，取得了更优的混淆成功率，表现通常比同类方法高15%；（3）混淆过程中无需来自目标AA分类器的直接信号；（4）利用独特的文体计量特征，可为可解释混淆提供合理的模型解释。我们还证明，ALISON能有效阻止四种SOTA AA方法准确判定ChatGPT生成文本的作者身份，同时仅对原始文本语义造成极小改变。为确保研究结果的可复现性，我们的代码和数据可在以下链接获取：https://github.com/EricX003/ALISON。
英文摘要：
Authorship Attribution (AA) and Authorship Obfuscation (AO) are two competing tasks of increasing importance in privacy research. Modern AA leverages an author's consistent writing style to match a text to its author using an AA classifier. AO is the corresponding adversarial task, aiming to modify a text in such a way that its semantics are preserved, yet an AA model cannot correctly infer its authorship. To address privacy concerns raised by state-of-the-art (SOTA) AA methods, new AO methods have been proposed but remain largely impractical to use due to their prohibitively slow training and obfuscation speed, often taking hours. To this challenge, we propose a practical AO method, ALISON, that (1) dramatically reduces training/obfuscation time, demonstrating more than 10x faster obfuscation than SOTA AO methods, (2) achieves better obfuscation success through attacking three transformer-based AA methods on two benchmark datasets, typically performing 15% better than competing methods, (3) does not require direct signals from a target AA classifier during obfuscation, and (4) utilizes unique stylometric features, allowing sound model interpretation for explainable obfuscation. We also demonstrate that ALISON can effectively prevent four SOTA AA methods from accurately determining the authorship of ChatGPT-generated texts, all while minimally changing the original text semantics. To ensure the reproducibility of our findings, our code and data are available at: https://github.com/EricX003/ALISON.
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。
