Xuyang Teng — accepted AI-conference papers

2026

FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training

Yuyuan Li, Junjie Fang, Fengyuan Yu, Xichun Sheng, Tianyu Du, Xuyang Teng +4

AAAI 2026technical

Federated Recommender Systems (FedRecs) leverage federated learning to protect user privacy by retaining data locally. However, user embeddings in FedRecs often encode sensitive attribute information, rendering them vulnerable to attribute inference attacks. Attribute unlearning has emerged as a pro

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Distill To Detect: Amplifying Anomalies in Backdoor Models through Knowledge Distillation

Chang Hu, Xuyang Teng, Wenpeng Xing, Han Chen, Chenhao Ye, Meng Han

ICASSP 2025accepted

Backdoor attacks represent a significant threat to the security of deep learning models. Due to the stealthiness of backdoor attacks, effectively detecting whether a model has been compromised by such attacks remains a major challenge. Previous backdoor detection methods either rely on backdoor data…

Cited by 0 Source ↗Scholar ↗