5 papers
SoK: Unlearnability and Unlearning for Model Dememorization
Mengying Zhang, Derui Wang, Ruoxi Sun +3
Advanced model dememorization methods, including availability poisoning (unlearnability) and machine unlearning, are emerging as key safeguards against data misuse in machine learn…
WinFLoRA: Incentivizing Client-Adaptive Aggregation in Federated LoRA under Privacy Heterogeneity
Mengsha Kou, Xiaoyu Xia, Ziqi Wang +4
Large Language Models (LLMs) increasingly underpin intelligent web applications, from chatbots to search and recommendation, where efficient specialization is essential. Low-Rank A…
Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks
Jiachen Li, Bang Wu, Xiaoyu Xia +3
Spiking Neural Networks (SNNs) have gained increasing attention for their superior energy efficiency compared to Artificial Neural Networks (ANNs). However, their security aspects,…
Edge Association Strategies for Synthetic Data Empowered Hierarchical Federated Learning with Non-IID Data
Jer Shyuan Ng, Aditya Pribadi Kalapaaking, Xiaoyu Xia +3
In recent years, Federated Learning (FL) has emerged as a widely adopted privacy-preserving distributed training approach, attracting significant interest from both academia and in…
Edge Unlearning is Not "on Edge"! An Adaptive Exact Unlearning System on Resource-Constrained Devices
Xiaoyu Xia, Ziqi Wang, Ruoxi Sun +3
The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. Removing data from the dataset alone…