Evade ChatGPT Detectors via A Single Space

Shuyang Cai, Wanyun Cui

Keywords: ChatGPT, AI-generated text, detector, large language model

Abstract: ChatGPT brings revolutionary social value but also raises concerns about the misuse of AI-generated text. Consequently, an important question is how to detect whether texts are generated by ChatGPT or by human. Existing detectors are built upon the assumption that there are distributional gaps between human-generated and AI-generated text. These gaps are typically identified using statistical information or classifiers. Our research challenges the distributional gap assumption in detectors. We find that detectors do not effectively discriminate the semantic and stylistic gaps between human-generated and AI-generated text. Instead, the "subtle differences", such as an extra space, become crucial for detection. Based on this discovery, we propose the SpaceInfi strategy to evade detection. Experiments demonstrate the effectiveness of this strategy across multiple benchmarks and detectors. We also provide a theoretical explanation for why SpaceInfi is successful in evading perplexity-based detection. And we empirically show that a phenomenon called token mutation causes the evasion for language model-based detectors. Our findings offer new insights and challenges for understanding and constructing more applicable ChatGPT detectors.

Primary Area: representation learning for computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6805