16 citations · 37 across the 9 of their papers we have counts for
10 papers
CAMF: Collaborative Adversarial Multi-agent Framework for Machine Generated Text Detection
Yue Wang, Liesheng Wei, Yuxiang Wang
Detecting machine-generated text (MGT) from contemporary Large Language Models (LLMs) is increasingly crucial amid risks like disinformation and threats to academic integrity. Exis…
SoK: Watermarking for AI-Generated Content
Xuandong Zhao, Sam Gunn, Miranda Christ +11
As the outputs of generative AI (GenAI) techniques improve in quality, it becomes increasingly challenging to distinguish them from human-created content. Watermarking schemes are…
Efficiently Identifying Watermarked Segments in Mixed-Source Texts
Xuandong Zhao, Chenwen Liao, Yu-Xiang Wang +1
Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing water…
Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
Xuandong Zhao, Lei Li, Yu-Xiang Wang
In this paper, we propose a new decoding method called Permute-and-Flip (PF) decoder. It enjoys stability properties similar to the standard sampling decoder, but is provably up to…
Weak-to-Strong Jailbreaking on Large Language Models
Xuandong Zhao, Xianjun Yang, Tianyu Pang +4
Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computati…
"Private Prediction Strikes Back!'' Private Kernelized Nearest Neighbors with Individual Renyi Filter
Yuqing Zhu, Xuandong Zhao, Chuan Guo +1
Most existing approaches of differentially private (DP) machine learning focus on private training. Despite its many advantages, private training lacks the flexibility in adapting…
Provable Robust Watermarking for AI-Generated Text
Xuandong Zhao, Prabhanjan Ananth, Lei Li +1
We study the problem of watermarking large language models (LLMs) generated text -- one of the most promising approaches for addressing the safety challenges of LLM usage. In this…
Protecting Language Generation Models via Invisible Watermarking
Xuandong Zhao, Yu-Xiang Wang, Lei Li
Language generation models have been an increasingly powerful enabler for many applications. Many such models offer free or affordable API access, which makes them potentially vuln…
Distillation-Resistant Watermarking for Model Protection in NLP
Xuandong Zhao, Lei Li, Yu-Xiang Wang
How can we protect the intellectual property of trained NLP models? Modern NLP models are prone to stealing by querying and distilling from their publicly exposed APIs. However, ex…
Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability
Hojjat Aghakhani, Dongyu Meng, Yu-Xiang Wang +2
A recent source of concern for the security of neural networks is the emergence of clean-label dataset poisoning attacks, wherein correctly labeled poison samples are injected into…