Defending Backdoor Attacks in Task-Oriented Multi-User Semantic Communication: A Contrastive Training Approach

Jincheng Peng, Huanlai Xing, Lexi Xu, Shouxi Luo, Penglin Dai, Li Feng, Laha Ale, Bowen Zhao 0002, Zhiwen Xiao. Defending Backdoor Attacks in Task-Oriented Multi-User Semantic Communication: A Contrastive Training Approach. IEEE Trans. Network Science and Engineering, 13:7376-7393, 2026. [doi]

Authors

Jincheng Peng

This author has not been identified. Look up 'Jincheng Peng' in Google

Huanlai Xing

This author has not been identified. Look up 'Huanlai Xing' in Google

Lexi Xu

This author has not been identified. Look up 'Lexi Xu' in Google

Shouxi Luo

This author has not been identified. Look up 'Shouxi Luo' in Google

Penglin Dai

This author has not been identified. Look up 'Penglin Dai' in Google

Li Feng

This author has not been identified. Look up 'Li Feng' in Google

Laha Ale

This author has not been identified. Look up 'Laha Ale' in Google

Bowen Zhao 0002

This author has not been identified. Look up 'Bowen Zhao 0002' in Google

Zhiwen Xiao

This author has not been identified. Look up 'Zhiwen Xiao' in Google