2 papers
cs.LG2026
Beyond the False Trade-off: Adaptive EWC for Stealthy and Generalizable T2I Backdoors
Lu Bowen, Xinyu Tang, Yin Yin Low +1
Preserving model fidelity is essential for stealthy text-to-image (T2I) backdoor attacks. Existing methods such as Learning without Forgetting (LwF) rely on output-based distillati…
cs.LG2023
Price of Stability in Quality-Aware Federated Learning
Yizhou Yan, Xinyu Tang, Chao Huang +1
Federated Learning (FL) is a distributed machine learning scheme that enables clients to train a shared global model without exchanging local data. The presence of label noise can…