4 papers
A First Order Meta Stackelberg Method for Robust Federated Learning (Technical Report)
Henger Li, Tianyi Xu, Tao Li +3
Recent research efforts indicate that federated learning (FL) systems are vulnerable to a variety of security breaches. While numerous defense strategies have been suggested, they…
Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editors
Henger Li, Shuangjie You, Flavio Di Palo +2
Tool calling enables large language models (LLMs) to interact with external environments through tool invocation, providing a practical way to overcome the limitations of pretraini…
Online Learning with Probing for Sequential User-Centric Selection
Tianyi Xu, Yiting Chen, Henger Li +3
We formalize sequential decision-making with information acquisition as the probing-augmented user-centric selection (PUCS) framework, where a learner first probes a subset of arms…
Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks
Tao Li, Henger Li, Yunian Pan +3
Federated learning (FL) is susceptible to a range of security threats. Although various defense mechanisms have been proposed, they are typically non-adaptive and tailored to speci…