Publications (59)
Less Is More -- Until It Breaks: Security Pitfalls of Vision Token Compression in Large Vision-Language Models
Xiaomei Zhang, Zhaoxi Zhang, Leo Yu Zhang +3
Visual token compression is widely adopted to improve the inference efficiency of Large Vision-Language Models (LVLMs), enabling their deployment in latency-sensitive and resource-…
Bounded and Unbiased Composite Differential Privacy
Kai Zhang, Yanjun Zhang, Ruoxi Sun +5
The objective of differential privacy (DP) is to protect privacy by producing an output distribution that is indistinguishable between any two neighboring databases. However, tradi…
ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery
Zirui Gong, Leo Yu Zhang, Yanjun Zhang +4
Federated Learning (FL) enables collaborative model training by sharing model updates instead of raw data, aiming to protect user privacy. However, recent studies reveal that these…
Memorization in deep learning: A survey
Jiaheng Wei, Yanjun Zhang, Leo Yu Zhang +5
Deep Learning (DL) powered by Deep Neural Networks (DNNs) has revolutionized various domains, yet understanding the intricacies of DNN decision-making and learning processes remain…
Block sampling Kaczmarz-Motzkin methods for consistent linear systems
Yanjun Zhang, Hanyu Li
The sampling Kaczmarz-Motzkin (SKM) method is a generalization of the randomized Kaczmarz and Motzkin methods. It first samples some rows of coefficient matrix randomly to build a…
Client-side Gradient Inversion Against Federated Learning from Poisoning
Jiaheng Wei, Yanjun Zhang, Leo Yu Zhang +5
Federated Learning (FL) enables distributed participants (e.g., mobile devices) to train a global model without sharing data directly to a central server. Recent studies have revea…