Yu Fu

Yu Fu

Auto-generated profile, based on publicly available information

Yu Fu

University of California Riverside

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YFYu Fu
Yu Fu
DXDeyi Xiong
Deyi Xiong
YDYue Dong
Yue Dong
To mitigate potential risks associated with language models (LMs), recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary restrictions and utilizing this information for detection. In this paper, we show that watermarking algorithms designed for LMs cannot be seamlessly applied to conditional text generation (CTG) tasks without a notable decline in downstream task performance. To address this issue, we introduce a simple yet effective semantic-aware watermarking algorithm that considers the characteristics of conditional text generation with the input context. Compared to the baseline watermarks, our proposed watermark yields significant improvements in both automatic and human evaluations across various text generation models, including BART and Flan-T5, for CTG tasks such as summarization and data-to-text generation. Meanwhile, it maintains detection ability with higher z-scores but lower AUC scores, suggesting the presence of a detection paradox that poses additional challenges for watermarking CTG.

16 October 2023 in arXiv
Verified
Preprint
Open access
PDF file
ESErfan Shayegani
Erfan Shayegani
AMAbdullah Al Mamun
Abdullah Al Mamun
YFYu Fu
Yu Fu
PZPedram Zaree
Pedram Zaree
YDYue Dong
Yue Dong
NANael Abu-Ghazaleh
Nael Abu-Ghazaleh
Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the emerging interdisciplinary field of adversarial attacks on LLMs, a subfield of trustworthy ML, combining the perspectives of Natural Language Processing and Security. Prior work has shown that even safety-aligned LLMs (via instruction tuning and reinforcement learning through human feedback) can be susceptible to adversarial attacks, which exploit weaknesses and mislead AI systems, as evidenced by the prevalence of `jailbreak' attacks on models like ChatGPT and Bard. In this survey, we first provide an overview of large language models, describe their safety alignment, and categorize existing research based on various learning structures: textual-only attacks, multi-modal attacks, and additional attack methods specifically targeting complex systems, such as federated learning or multi-agent systems. We also offer comprehensive remarks on works that focus on the fundamental sources of vulnerabilities and potential defenses. To make this field more accessible to newcomers, we present a systematic review of existing works, a structured typology of adversarial attack concepts, and additional resources, including slides for presentations on related topics at the 62nd Annual Meeting of the Association for Computational Linguistics (ACL'24).

1 January 2024
Verified
Conference Paper
Open access
PDF file
YFYu Fu
Yu Fu
ESErfan Shayegan
Erfan Shayegan
MAMamun Al Abdullah
Mamun Al Abdullah
PZPedram Zaree
Pedram Zaree
NANael Abu-Ghazaleh
Nael Abu-Ghazaleh
YDYue Dong
Yue Dong
Yu Fu, Erfan Shayegan, Md. Mamun Al Abdullah, Pedram Zaree, Nael Abu-Ghazaleh, Yue Dong. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 5: Tutorial Abstracts). 2024.

1 January 2023
Verified
Conference Paper
Open access
PDF file
YFYu Fu
Yu Fu
DXDeyi Xiong
Deyi Xiong
YDYue Dong
Yue Dong
Yu Fu, Deyi Xiong, Yue Dong. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.

15 June 2025
Verified
Book Chapter
Closed access
PDF file
YLYiran Luo
Yiran Luo
HPHet Patel
Het Patel
YFYu Fu
Yu Fu
DADawon Ahn
Dawon Ahn
JCJia Chen
Jia Chen
EPEvangelos E. Papalexakis
Evangelos E. Papalexakis

13 February 2024 in arXiv
Verified
Preprint
Open access
PDF file
YFYu Fu
Yu Fu
DXDeyi Xiong
Deyi Xiong
YDYue Dong
Yue Dong
To mitigate potential risks associated with language models, recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary restrictions and utilizing this information for detection. While these watermarks only induce a slight deterioration in perplexity, our empirical investigation reveals a significant detriment to the performance of conditional text generation. To address this issue, we introduce a simple yet effective semantic-aware watermarking algorithm that considers the characteristics of conditional text generation and the input context. Experimental results demonstrate that our proposed method yields substantial improvements across various text generation models, including BART and Flan-T5, in tasks such as summarization and data-to-text generation while maintaining detection ability.