4 papers
Topology-Independent Robustness of the Weighted Mean under Label Poisoning Attacks in Heterogeneous Decentralized Learning
Jie Peng, Weiyu Li, Stefan Vlaski +1
Robustness to malicious attacks is crucial for practical decentralized signal processing and machine learning systems. A typical example of such attacks is label poisoning, meaning…
Binary and Ternary Quantization Can Enhance Feature Discrimination
Weizhi Lu, Mingrui Chen, Weiyu Li
Quantization is widely applied in machine learning to reduce computational and storage costs for both data and models. Considering that classification tasks are fundamental to the…
Data-adaptive Safety Rules for Training Reward Models
Xiaomin Li, Mingye Gao, Zhiwei Zhang +2
Reinforcement Learning from Human Feedback (RLHF) is commonly employed to tailor models to human preferences, especially to improve the safety of outputs from large language models…
Mean Aggregator is More Robust than Robust Aggregators under Label Poisoning Attacks on Distributed Heterogeneous Data
Jie Peng, Weiyu Li, Stefan Vlaski +1
Robustness to malicious attacks is of paramount importance for distributed learning. Existing works usually consider the classical Byzantine attacks model, which assumes that some…