13 papers
Auditing Agent Harness Safety
Chengzhi Liu, Yichen Guo, Yepeng Liu +8
LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a c…
Fundamental Trade-Offs in Multi-Bit Watermarking of Stochastic Processes
Haiyun He, Yepeng Liu, Zhuoer Shen +3
We study multi-bit watermarking for data generated by stochastic processes, where a hidden message is embedded during sampling and must be decodable by an authorized detector that…
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
Zhen Zhang, Changyi Yang, Zijie Xia +11
Tokens are the fundamental units of computation in modern autoregressive models, and generation length directly influences both inference cost and reasoning performance. Despite it…
Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
Yepeng Liu, Xuandong Zhao, Dawn Song +2
Despite progress in watermarking algorithms for large language models (LLMs), real-world deployment remains limited. We argue that this gap stems from misaligned incentives among L…
In-Context Watermarks for Large Language Models
Yepeng Liu, Xuandong Zhao, Christopher Kruegel +2
The growing use of large language models (LLMs) for sensitive applications has highlighted the need for effective watermarking techniques to ensure the provenance and accountabilit…
TokenPure: Watermark Removal through Tokenized Appearance and Structural Guidance
Pei Yang, Yepeng Liu, Kelly Peng +2
In the digital economy era, digital watermarking serves as a critical basis for ownership proof of massive replicable content, including AI-generated and other virtual assets. Desi…