TY - GEN
T1 - How Reliable Are AI-Generated-Text Detectors? An Assessment Framework Using Evasive Soft Prompts
AU - Kumarage, Tharindu
AU - Sheth, Paras
AU - Moraffah, Raha
AU - Garland, Joshua
AU - Liu, Huan
N1 - Publisher Copyright: © 2023 Association for Computational Linguistics.
PY - 2023
Y1 - 2023
N2 - In recent years, there has been a rapid proliferation of AI-generated text, primarily driven by the release of powerful pre-trained language models (PLMs). To address the issue of misuse associated with AI-generated text, various high-performing detectors have been developed, including the OpenAI detector and the Stanford DetectGPT. In our study, we ask how reliable these detectors are. We answer the question by designing a novel approach that can prompt any PLM to generate text that evades these high-performing detectors. The proposed approach suggests a universal evasive prompt, a novel type of soft prompt, which guides PLMs in producing "human-like" text that can mislead the detectors. The novel universal evasive prompt is achieved in two steps: First, we create an evasive soft prompt tailored to a specific PLM through prompt tuning; and then, we leverage the transferability of soft prompts to transfer the learned evasive soft prompt from one PLM to another. Employing multiple PLMs in various writing tasks, we conduct extensive experiments to evaluate the efficacy of the evasive soft prompts in their evasion of state-of-the-art detectors.
AB - In recent years, there has been a rapid proliferation of AI-generated text, primarily driven by the release of powerful pre-trained language models (PLMs). To address the issue of misuse associated with AI-generated text, various high-performing detectors have been developed, including the OpenAI detector and the Stanford DetectGPT. In our study, we ask how reliable these detectors are. We answer the question by designing a novel approach that can prompt any PLM to generate text that evades these high-performing detectors. The proposed approach suggests a universal evasive prompt, a novel type of soft prompt, which guides PLMs in producing "human-like" text that can mislead the detectors. The novel universal evasive prompt is achieved in two steps: First, we create an evasive soft prompt tailored to a specific PLM through prompt tuning; and then, we leverage the transferability of soft prompts to transfer the learned evasive soft prompt from one PLM to another. Employing multiple PLMs in various writing tasks, we conduct extensive experiments to evaluate the efficacy of the evasive soft prompts in their evasion of state-of-the-art detectors.
UR - http://www.scopus.com/inward/record.url?scp=85183288578&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85183288578&partnerID=8YFLogxK
M3 - Conference contribution
T3 - Findings of the Association for Computational Linguistics: EMNLP 2023
SP - 1337
EP - 1349
BT - Findings of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
T2 - 2023 Findings of the Association for Computational Linguistics: EMNLP 2023
Y2 - 6 December 2023 through 10 December 2023
ER -