3 papers
cs.CL2025
FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models
Yan Gao, Massimo Roberto Scamarcia, Javier Fernandez-Marques +18
Large Language Models (LLMs) have achieved state-of-the-art results across diverse domains, yet their development remains reliant on vast amounts of publicly available data, raisin…
cs.CR2025
Sybil-based Virtual Data Poisoning Attacks in Federated Learning
Changxun Zhu, Qilong Wu, Lingjuan Lyu +1
Federated learning is vulnerable to poisoning attacks by malicious adversaries. Existing methods often involve high costs to achieve effective attacks. To address this challenge, w…
cs.LG2025
SacFL: Self-Adaptive Federated Continual Learning for Resource-Constrained End Devices
Zhengyi Zhong, Weidong Bao, Ji Wang +3
The proliferation of end devices has led to a distributed computing paradigm, wherein on-device machine learning models continuously process diverse data generated by these devices…