3 citations · 3 across the 3 of their papers we have counts for
4 papers
ECHO: Replacing the Compliance Proxy with Response Harmfulness in Optimization-Based Jailbreak Attack
Yuanwei Wu, Lingdong Huang, Yunlong Mao +3
Despite extensive safety alignment, large language models remain vulnerable to jailbreak attacks. Existing optimization-based attacks share a single objective: maximize a token-lev…
Gradient Mirage: Trainable yet Label-Unidentifiable Gradients in Large Language Model Split Learning
Shiyu Miao, Yunlong Mao, Zirui Huang +5
Gradient matching attacks (GMAs) in LLM split learning (SL) rely on a critical yet underexplored assumption: the gradient exposed at the split interface is a faithful derivative of…
Auditing Data Provenance in LLM Fine-tuning via Intrinsic Distributional Fingerprints
Zirui Huang, Yunlong Mao, Wei Tong +3
The proliferation of customized Large Language Models (LLMs) poses critical risks of Data Intellectual Property (Data IP) infringement via unauthorized fine-tuning on proprietary d…
A Split-and-Privatize Framework for Large Language Model Fine-Tuning
Xicong Shen, Yang Liu, Huiqi Liu +6
Fine-tuning is a prominent technique to adapt a pre-trained language model to downstream scenarios. In parameter-efficient fine-tuning, only a small subset of modules are trained o…