4 papers
On the Out-of-Distribution Backdoor Attack for Federated Learning
Jiahao Xu, Zikai Zhang, Rui Hu
Traditional backdoor attacks in federated learning (FL) operate within constrained attack scenarios, as they depend on visible triggers and require physical modifications to the ta…
Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
Yansi Li, Jiahao Xu, Tian Liang +8
Enhancing the reasoning capabilities of large language models (LLMs), particularly for complex tasks requiring multi-step logical deductions, remains a significant challenge. Tradi…
Teaching LLMs to Refine with Tools
Dian Yu, Yuheng Zhang, Jiahao Xu +5
Large language models (LLMs) can refine their responses based on feedback, enabling self-improvement through iterative training or test-time refinement. However, existing methods p…
Identify Backdoored Model in Federated Learning via Individual Unlearning
Jiahao Xu, Zikai Zhang, Rui Hu
Backdoor attacks present a significant threat to the robustness of Federated Learning (FL) due to their stealth and effectiveness. They maintain both the main task of the FL system…