Xixiang Lyu

According to our database, Xixiang Lyu authored at least 10 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models.

Peihai Jiang, Xixiang Lyu, Yige Li, Jing Ma

Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024

Learning from Distinction: Mitigating Backdoors Using a Low-Capacity Model.

Haosen Sun, Yiming Li, Xixiang Lyu, Jing Ma

Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

2023

BCMIX: A Blockchain-Based Dynamic Self-Reconfigurable Mixnet.

Renpeng Zou, Xixiang Lyu, Jing Ma, Bowen Zhang, Danfang Wu

IEEE/ACM Trans. Netw., October, 2023

Reconstructive Neuron Pruning for Backdoor Defense.

Yige Li, Xixiang Lyu, Xingjun Ma, Nodens Koren, Lingjuan Lyu, Bo Li, Yu-Gang Jiang

Proceedings of the International Conference on Machine Learning, 2023

2022

FLEAM: A Federated Learning Empowered Architecture to Mitigate DDoS in Industrial IoT.

Jianhua Li, Lingjuan Lyu, Ximeng Liu, Xuyun Zhang, Xixiang Lyu

IEEE Trans. Ind. Informatics, 2022

Privacy-preserving federated learning based on multi-key homomorphic encryption.

Jing Ma, Si-Ahmed Naas, Stephan Sigg, Xixiang Lyu

Int. J. Intell. Syst., 2022

Natural Backdoor Attacks on Speech Recognition Models.

Jinwen Xin, Xixiang Lyu, Jing Ma

Proceedings of the Machine Learning for Cyber Security - 4th International Conference, 2022

2021

A Novel Variable K-Pseudonym Scheme Applied to 5G Anonymous Access Authentication.

Dong Ma, Xixiang Lyu, Renpeng Zou

CoRR, 2021

Anti-Backdoor Learning: Training Clean Models on Poisoned Data.

Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Xingjun Ma

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks.

Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Xingjun Ma

Proceedings of the 9th International Conference on Learning Representations, 2021