papers

Publications (59)

cs.CR2026

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-…

cs.CR2023

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…

cs.LG2026

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…

cs.LG2024

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…

math.NA2020

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…

cs.CR2023

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…