Hello World.
Hi! This is Yanghao ZHANG, a researcher & a software engineer.
I am a Research Associate at Safe Artificial Intelligence Lab (SAIL), Imperial College London, working under the supervision of Prof. Alessio Lomuscio. I have completed my PhD study at Trustworthy ACPS Lab, University of Liverpool, supervised by Prof. Wenjie Ruan and Prof. Xiaowei Huang. Before transferring to Liverpool, I start my PhD study in September 2020 at University of Exeter. My research interests include adversarial attacks/defenses, safety verification and robust machine learning applications. Before starting my PhD, I achieved MSc Artificial Intelligence with distinction at University of Southampton, and BEng Software Engineering from Huizhou University.
Recent News
2024
-
- (09/2024) I will be joining Safe Artificial Intelligence Lab (SAIL) at Imperial College London as a Research Associate, working under the supervision of Prof. Alessio Lomuscio.
-
- (08/2024) Have been invited as a reviewer for ICLR 2025.
-
- (06/2024) Our survey paper "A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation" has been accepted by Artificial Intelligence Review.
-
- (06/2024) We conduct a survey about building guardrails for foundation models (LLMs) .
-
- (05/2024) Have been invited as a reviewer for journals The Visual Computer and Machine Vision and Applications.
-
- (05/2024) Have been invited as a reviewer for NeurIPS 2024.
-
- (04/2024) Our paper "PRASS: Probabilistic Risk-averse Robust Learning with Stochastic Search" has been accepted by IJCAI 2024.
-
- (02/2024) Our paper "Towards Fairness-Aware Adversarial Learning" has been accepted by CVPR 2024.
-
- (02/2024) Have been invited as a reviewer for ECCV 2024.
-
- (01/2024) Have been invited as a reviewer for Information Sciences.
2023
-
- (12/2023) Our paper "DeepGRE: Global Robustness Evaluaion of Deep Neural Networks" has been accepted by ICASSP 2024.
-
- (12/2023) Our paper "Reward Certification for Policy Smoothed Reinforcement Learning" has been accepted by AAAI 2024.
-
- (05/2023) Have been invited as a reviewer for TKDE.
-
- (05/2023) Our paper "Self-adaptive Adversarial Training for Robust Medical Segmentation" has been accepted by MICCAI 2023.
-
- (01/2023) Start a Research Associate position at University of Liverpool under the supervision of Prof. Xiaowei Huang.
2022
-
- (11/2022) Move to University of Liverpool to continue my PhD study.
