NL Seminar -Red Teaming Language Model Detectors with Language Models

Speaker: Yihan Wang, UCLA

Talk Title: Red Teaming Language Model Detectors with Language Models

Series: NL Seminar

Abstract: REMINDER: This talk will be a live presentation only, it will not be recorded.  Meeting hosts only admit guests that they know to the Zoom meeting. Hence, you’re highly encouraged to use your USC account to sign into Zoom. If you’re an outside visitor, please provide your: Full Name, Title and Name of Workplace to (nlg-seminar-host(at)isi.edu) beforehand so we’ll be aware of your attendance. Also, let us know if you plan to attend in-person or virtually. More Info for NL Seminars can be found at: https://nlg.isi.edu/nl-seminar/  The prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive usage of LLMs, recent works have proposed algorithms to detect LLM-generated text and protect LLMs. In this paper, we investigate the robustness and reliability of these LLM detectors under adversarial attacks. We study two types of attack strategies: 1) replacing certain words in an LLM's output with their synonyms given the context; 2) automatically searching for an instructional prompt to alter the writing style of the generation. In both strategies, we leverage an auxiliary LLM to generate the word replacements or the instructional prompt. Different from previous works, we consider a challenging setting where the auxiliary LLM can also be protected by a detector. Experiments reveal that our attacks effectively compromise the performance of all detectors in the study with plausible generations, underscoring the urgent need to improve the robustness of LLM-generated text detection systems. This talk may also introduce some of our other recent works on trustworthy and ethical LLMs.

Biography: Yihan is Ph.D. student at UCLA in Computer Science. She received her B.Eng. degree in Computer Science and Technology from Tsinghua University in June 2020. Ms. Wang's research interest is machine learning, especially improving trustworthiness and generalization of machine learning models. Yihan is currently working with Prof. Cho-Jui Hsieh at UCLA. If speaker approves to be recorded for this NL Seminar talk, it will be posted on our USC/ISI YouTube page within 1-2 business days: https://www.youtube.com/user/USCISI. Subscribe here to learn more about upcoming seminars: https://www.isi.edu/events/

Host: Jon May and Justin Cho

More Info: https://nlg.isi.edu/nl-seminar/

Webcast: https://youtu.be/Fx1T9lyNDh0?si=qEL0QipveladKDwP

Location: Information Science Institute (ISI) - Virtual and ISI-Conf Rm#689

WebCast Link: https://youtu.be/Fx1T9lyNDh0?si=qEL0QipveladKDwP

Audiences: Everyone Is Invited

Contact: Pete Zamar

Event Link: https://nlg.isi.edu/nl-seminar/