Xi Li

According to our database, Xi Li authored at least 10 papers between 2020 and 2024.

Collaborative distances:

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

2024

Universal Post-Training Reverse-Engineering Defense Against Backdoors in Deep Neural Networks.

Xi Li, Hang Wang, David J. Miller, George Kesidis

CoRR, 2024

Temporal-Distributed Backdoor Attack against Video Based Action Recognition.

Xi Li, Songhe Wang, Ruiquan Huang, Mahanth Gowda, George Kesidis

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Backdoor Mitigation by Correcting the Distribution of Neural Activations.

Xi Li, Zhen Xiang, David J. Miller, George Kesidis

CoRR, 2023

A BIC-Based Mixture Model Defense Against Data Poisoning Attacks on Classifiers.

Xi Li, David J. Miller, Zhen Xiang, George Kesidis

Proceedings of the 33rd IEEE International Workshop on Machine Learning for Signal Processing, 2023

2022

Detecting Backdoor Attacks against Point Cloud Classifiers.

Zhen Xiang, David J. Miller, Siheng Chen, Xi Li, George Kesidis

Proceedings of the IEEE International Conference on Acoustics, 2022

Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks.

Xi Li, Zhen Xiang, David J. Miller, George Kesidis

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

Backdoor Attack and Defense for Deep Regression.

Xi Li, George Kesidis, David J. Miller, Vladimir Lucic

CoRR, 2021

Robust and Active Learning for Deep Neural Network Regression.

Xi Li, George Kesidis, David J. Miller, Maxime Bergeron, Ryan Ferguson, Vladimir Lucic

CoRR, 2021

A Backdoor Attack against 3D Point Cloud Classifiers.

Zhen Xiang, David J. Miller, Siheng Chen, Xi Li, George Kesidis

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2020

A Scalable Mixture Model Based Defense Against Data Poisoning Attacks on Classifiers.

Xi Li, David J. Miller, Zhen Xiang, George Kesidis

Proceedings of the Dynamic Data Driven Applications Systems, 2020