paper-conference

Adapter-Based Parameter-Efficient Adversarial Training for Enhanced Clean Accuracy

Adversarial training has emerged as a leading defense against adversarial attacks in deep learning, but suffers from a fundamental …

Xiaowen Li, Wenwei Zhao, Yao liu, Zhuo Lu

Consistency-Preserving Logit Shaping for Robust Model Stealing Defense with Applications in Wireless Spectrum Security

Model stealing (model extraction) threatens ML-as-a-service APIs by enabling adversaries to reconstruct proprietary models from queried …

Xiaowen Li, Wenwei Zhao, Yao liu, Zhuo Lu

Malicious Forgetting: Backdoor Injection in Active Federated Unlearning and Countermeasure Design

Federated learning (FL) enables collaborative model training without sharing raw data, but also raises increasing demands for the right …

Wenwei Zhao, Yuanzhe Peng, Xiaowen Li, Jie Xu, Yao Liu, Zhuo Lu

Adversarial Update-Based Federated Unlearning for Poisoned Model Recovery

Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients upload manipulated updates to degrade the …

Wenwei Zhao, Xiaowen Li, Yao Liu, Zhuo Lu

Adversarial Update-Based Federated Unlearning for Poisoned Model Recovery

Equilibrium-Driven Vertical Federated Learning with Selective Privacy Protection

Vertical Federated Learning (VFL) enables multiple clients with feature-partitioned data to collaboratively train models while …

Yuanzhe Peng, Wenwei Zhao, Zhuo Lu, Jie Xu

Equilibrium-Driven Vertical Federated Learning with Selective Privacy Protection

Detecting Adversarial Spectrum Attacks via Distance to Decision Boundary Statistics

In this paper, we propose an efficient framework for detecting adversarial spectrum attacks. Our design leverages the concept of the …

Wenwei Zhao, Xiaowen Li, Shangqing Zhao, Jie Xu, Yao liu, Zhuo Lu

Detecting Adversarial Spectrum Attacks via Distance to Decision Boundary Statistics