通过清理嵌入空间有害子空间，提升文本生成检测的跨域鲁棒性
Robust AI-Generated Text Detection by Restricted Embeddings
- 移除Transformer嵌入空间中的有害线性子空间，避免依赖特定领域特征
- 在未见生成器和语境下，检测准确率提升最多14%
- 适合需要跨模型、跨领域检测的AI内容安全场景
随着AI生成文本的数量和质量不断提升，检测难度显著增加。在真实场景中，生成文本的领域（风格与主题）和生成模型往往未知。本文聚焦基于分类器的文本生成检测器的鲁棒性，即其对未见生成器或语义领域的迁移能力。我们研究了基于Transformer的文本编码器嵌入空间的几何结构，发现清除有害线性子空间有助于训练出忽略领域特异性伪特征的鲁棒分类器。通过多种子空间分解与特征选择策略，我们在跨域和跨生成器迁移任务中显著优于现有方法。针对RoBERTa和BERT嵌入，采用逐头和坐标级子空间移除的最佳方案，在特定设置下将平均分布外（OOD）分类得分分别提升最高9%和14%。代码与数据已公开：https://github.com/SilverSolver/RobustATD
原文摘要 · Abstract (English)
Growing amount and quality of AI-generated texts makes detecting such content more difficult. In most real-world scenarios, the domain (style and topic) of generated data and the generator model are not known in advance. In this work, we focus on the robustness of classifier-based detectors of AI-generated text, namely their ability to transfer to unseen generators or semantic domains. We investigate the geometry of the embedding space of Transformer-based text encoders and show that clearing out harmful linear subspaces helps to train a robust classifier, ignoring domain-specific spurious features. We investigate several subspace decomposition and feature selection strategies and achieve significant improvements over state of the art methods in cross-domain and cross-generator transfer. Our best approaches for head-wise and coordinate-based subspace removal increase the mean out-of-distribution (OOD) classification score by up to 9% and 14% in particular setups for RoBERTa and BERT embeddings respectively. We release our code and data: https://github.com/SilverSolver/RobustATD
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。