Dr Ronghui Mu

Computer Science

Work email Ronghui.Mu@liverpool.ac.uk

Publications

Filter the publication list

Filter list by type

Show all
Journal article
Conference paper
Chapter
Other

2024

3DVerifier: efficient robustness verification for 3D point cloud models (Journal article)

Mu, R., Ruan, W., Marcolino, L. S., & Ni, Q. (2024). 3DVerifier: efficient robustness verification for 3D point cloud models. Machine Learning, 113(4), 1771-1798. doi:10.1007/s10994-022-06235-3

DOI: 10.1007/s10994-022-06235-3

Enhancing robustness in video recognition models: Sparse adversarial attacks and beyond. (Journal article)

Mu, R., Marcolino, L., Ni, Q., & Ruan, W. (2024). Enhancing robustness in video recognition models: Sparse adversarial attacks and beyond.. Neural networks : the official journal of the International Neural Network Society, 171, 127-143. doi:10.1016/j.neunet.2023.11.056

DOI: 10.1016/j.neunet.2023.11.056

Towards Fairness-Aware Adversarial Learning (Preprint)

Building Guardrails for Large Language Models (Preprint)

Nrat: towards adversarial training with inherent label noise (Journal article)

Chen, Z., Wang, F., Mu, R., Xu, P., Huang, X., & Ruan, W. (2024). Nrat: towards adversarial training with inherent label noise. Machine Learning. doi:10.1007/s10994-023-06437-3

DOI: 10.1007/s10994-023-06437-3

2023

Reward Certification for Policy Smoothed Reinforcement Learning (Preprint)

Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning (Conference Paper)

Mu, R., Ruan, W., Marcolino, L. S., Jin, G., & Ni, Q. (2023). Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning. In Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023 Vol. 37 (pp. 15046-15054).

A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation (Preprint)

Randomized Adversarial Training via Taylor Expansion (Preprint)

DOI: 10.48550/arxiv.2303.10653

Randomized Adversarial Training via Taylor Expansion (Conference Paper)

Jin, G., Yi, X., Wu, D., Mu, R., & Huang, X. (2023). Randomized Adversarial Training via Taylor Expansion. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. doi:10.1109/cvpr52729.2023.01578

DOI: 10.1109/cvpr52729.2023.01578

2022

Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning (Preprint)

DOI: 10.48550/arxiv.2212.11746

3DVerifier: Efficient Robustness Verification for 3D Point Cloud Models (Preprint)

DOI: 10.48550/arxiv.2207.07539

2021

Sparse Adversarial Video Attacks with Spatial Transformations (Preprint)

DOI: 10.48550/arxiv.2111.05468