用嵌入向量生成对抗文本，让AI写作更难被检测。
Adversarial Attacks on AI-Generated Text Detection Models: A Token Probability-Based Approach Using Embeddings
- 基于嵌入相似性与同义词替换，重构AI生成文本。
- 在XSum和SQuAD数据集上，检测得分分别降至0.2744和0.3532。
- 可为检测模型提供鲁棒性测试，适合安全与评估研究者。
近年来，利用人工智能的文本生成工具在学生报告、创意写作等场景中偶有滥用，促使抄袭检测服务需提升识别AI生成内容的能力。对抗攻击常用于测试AI文本检测模型的鲁棒性。本文提出一种针对检测模型（如Fast-DetectGPT）的新文本对抗攻击方法，利用嵌入模型进行数据扰动，旨在重构生成文本以降低其被识破的概率。具体地，采用多种嵌入技术，包括可解释机器学习中的Tsetlin Machine（TM），结合同义词与嵌入相似性向量，实现对检测模型的高效攻击。实验表明，在XSum数据集上，检测分数从0.4431下降至0.2744 AUROC；在SQuAD数据集上，从0.5068降至0.3532 AUROC，达到当前最优效果。
原文摘要 · Abstract (English)
In recent years, text generation tools utilizing Artificial Intelligence (AI) have occasionally been misused across various domains, such as generating student reports or creative writings. This issue prompts plagiarism detection services to enhance their capabilities in identifying AI-generated content. Adversarial attacks are often used to test the robustness of AI-text generated detectors. This work proposes a novel textual adversarial attack on the detection models such as Fast-DetectGPT. The method employs embedding models for data perturbation, aiming at reconstructing the AI generated texts to reduce the likelihood of detection of the true origin of the texts. Specifically, we employ different embedding techniques, including the Tsetlin Machine (TM), an interpretable approach in machine learning for this purpose. By combining synonyms and embedding similarity vectors, we demonstrates the state-of-the-art reduction in detection scores against Fast-DetectGPT. Particularly, in the XSum dataset, the detection score decreased from 0.4431 to 0.2744 AUROC, and in the SQuAD dataset, it dropped from 0.5068 to 0.3532 AUROC.
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。