4 papers
TOFD: Target-Oriented Feature Decoupling against Poisoning Attacks in Split Federated Learning
Yuhan Xie, Jingrong Huang, Chen Lyu
Split Federated Learning (SFL) facilitates privacy-preserving collaborative training with reduced client-side overhead. However, its split architecture introduces unique attack sur…
Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation
Joakim Edin, Casper L. Christensen, Róbert Csordás +5
Circuit localization methods aim to identify the subset of model components responsible for specific behaviors in large language models, enabling detailed mechanistic analysis. Mos…
BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
Yuhan Xie, Chen Lyu, Jingrong Huang
Split Federated Learning (SFL) enables privacy-preserving collaborative training by partitioning models between clients and a server. However, under non-IID data distributions, SFL…
A Plug-and-Play Bregman ADMM Module for Inferring Event Branches in Temporal Point Processes
Qingmei Wang, Yuxin Wu, Yujie Long +4
An event sequence generated by a temporal point process is often associated with a hidden and structured event branching process that captures the triggering relations between its…