Cheng-Chang Tsai — accepted AI-conference papers

2026

FedSDA: Federated Stain Distribution Alignment for Non-IID Histopathological Image Classification

Cheng-Chang Tsai, Kai-Wen Cheng, Chun-Shien Lu

AAAI 2026technical

Federated learning (FL) has shown success in collaboratively training a model among decentralized data resources without directly sharing privacy-sensitive training data. Despite recent advances, non-IID (non-independent and identically distributed) data poses an inevitable challenge that hinders th

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Defending against Clean-Image Backdoor Attack in Multi-Label Classification

Cheng-Yi Lee, Cheng-Chang Tsai, Ching-Chia Kao, Chun-Shien Lu, Chia-Mu Yu

ICASSP 2024accepted

Deep neural networks (DNNs) are known to be vulnerable to backdoor attacks. Specifically, the attacker endeavors to implant backdoors in the DNN model by injecting a set of poisoning samples such that the malicious model predicts target labels once the backdoor is triggered. The clean-image attack h…

Cited by 0 Source ↗Scholar ↗