16 citations · 28 across the 6 of their papers we have counts for
6 papers
How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment
Rui Zhu, Weiheng Bai, Qiushi Wu +3
Reinforcement Learning (RL) has emerged as a crucial paradigm for unlocking the advanced reasoning capabilities of Large Language Models (LLMs), encompassing frameworks like RLHF a…
The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks
Xiaoyi Chen, Siyuan Tang, Rui Zhu +7
The rapid advancements of large language models (LLMs) have raised public concerns about the privacy leakage of personally identifiable information (PII) within their extensive tra…
Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering
Rui Zhu, Di Tang, Siyuan Tang +4
Most existing methods to detect backdoored machine learning (ML) models take one of the two approaches: trigger inversion (aka. reverse engineer) and weight analysis (aka. model di…
Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models
Rui Zhu, Di Tang, Siyuan Tang +2
In this paper, we present a simple yet surprisingly effective technique to induce "selective amnesia" on a backdoored model. Our approach, called SEAM, has been inspired by the pro…
Understanding Impacts of Task Similarity on Backdoor Attack and Detection
Di Tang, Rui Zhu, XiaoFeng Wang +2
With extensive studies on backdoor attack and detection, still fundamental questions are left unanswered regarding the limits in the adversary's capability to attack and the defend…
Bounding The Number of Linear Regions in Local Area for Neural Networks with ReLU Activations
Rui Zhu, Bo Lin, Haixu Tang
The number of linear regions is one of the distinct properties of the neural networks using piecewise linear activation functions such as ReLU, comparing with those conventional on…