activity
20232026
most citedDeepTheft: Stealing DNN Model Architectures through Power Side Channel

2 citations · 5 across the 18 of their papers we have counts for

collaborators
Showing cs.CRShow all

11 papers · 1 filter

cs.CR2026

SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models

Bingxin Xu, Yuzhang Shang, Binghui Wang +1

Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain underexplored. We identify a fundam…

cs.CR2025

Practical, Generalizable and Robust Backdoor Attacks on Text-to-Image Diffusion Models

Haoran Dai, Jiawen Wang, Ruo Yang +4

Text-to-image diffusion models (T2I DMs) have achieved remarkable success in generating high-quality and diverse images from text prompts, yet recent studies have revealed their vu…

cs.CR2025

Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective

Nima Naderloui, Shenao Yan, Binghui Wang +4

Machine unlearning focuses on efficiently removing specific data from trained models, addressing privacy and compliance concerns with reasonable costs. Although exact unlearning en…

cs.CR2025

Backdoor Attacks on Discrete Graph Diffusion Models

Jiawen Wang, Samin Karim, Yuan Hong +1

Diffusion models are powerful generative models in continuous data domains such as image and video data. Discrete graph diffusion models (DGDMs) have recently extended them for gra…

cs.CR2024

FedGMark: Certifiably Robust Watermarking for Federated Graph Learning

Yuxin Yang, Qiang Li, Yuan Hong +1

Federated graph learning (FedGL) is an emerging learning paradigm to collaboratively train graph data from various clients. However, during the development and deployment of FedGL…

cs.CR2024

Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspective

Zifan Wang, Binghui Zhang, Meng Pang +2

Federated learning (FL) is an emerging collaborative learning paradigm that aims to protect data privacy. Unfortunately, recent works show FL algorithms are vulnerable to the serio…