News

2024

(02/2024) Our TACPS lab is honoured to join as a member to the AI Safety Institute Consortium (AISIC) that is established by the National Institute of Standards and Technology (NIST) to support the development and deployment of safe and trustworthy artificial intelligence (AI).
(01/2024) Our paper Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems is accepted by IEEE Robotics and Automation Letters. Congrats Dr. Yi Dong and all co-authors!
(01/2024) Our new project, SLLM: Safeguarding Large Language Models funded by Alan Turing Institute, has officially started. PI: Dr. Yi Dong, Co-I: Prof. Xiaowei Huang, Dr. Ronghui Mu.
(01/2024) Congradulations to Dr. Yi Dong and all Co-Investigators! Our project CSEA: Creating Safe and Explanable AI has lanuched.

2023

(10/2023) We won an Alan Turing project “CRoCS: Certified Robust and Scalable Autonomous Operation in Cyber Space”, funded from The AI for Cyber Defence (AICD) Research Centre. It will start from 1st December, 2023.
(09/2023) Our journal paper Hierarchical Distribution-Aware Testing of Deep Learning is accepted by ACM Transactions on Software Engineering and Methodology.
(07/2023) Paper SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability accepted to ICCV2023, congrats to Wei and co-authors.
(03/2023) Our team at University of Liverpool wins the Special Recognition Award for novel modelling/design of the UK-US Privacy-Enhancing Technologies Prize Challenges.
(02/2023) Paper Randomized adversarial training via taylor expansion accepted to CVPR2023, congrats to Gaojie and co-authors.
(01/2023) Paper Decentralised and Cooperative Control of Multi-Robot Systems through Distributed Optimisation accepted to AAMAS2023, congrats to Yi and co-authors.

2022

(12/2022) The textbook “Machine Learning Safety”, written by Professor Xiaowei Huang, Mr. Gaojie Jin, and Dr. Wenjie Ruan, will be published in December 2022.
(11/2022) Our Trustworthy ACPS Github Address has been released, please keep focusing on the update of our lab work.
(11/2022) Our new project, SPACE: fully decentralised distributed learning for tradeoff of privacy, accuracy, communication complexity, and efficiency, has officially started. PI: Prof Xiaowei Huang, Co-I: Dr Xingyu Zhao, Dr Yi Dong.
(10/2022) Our paper “Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance”, has been published on ACM Transactions on Embedded Computing Systems. Congratulations to Dr. Yi Dong!
(06/2022) Congratulations to Dr. Yi Dong! Our paper “Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems” has been accepted to IROS2022.
(06/2022) Congratulations to Kaiwen Cai! Our paper “STUN: Self-Teaching Uncertainty Estimation for Place Recognition” has been accepted to IROS2022.
(06/2022) Congratulations to Yi Qi, whose paper on “A Hierarchical HAZOP-Like Safety Analysis for Learning-Enabled Systems” was accepted by AISafety Workshop at IJCAI2022!
(05/2022) Congratulations to Dengyu Wu, whose paper “A Little Energy Goes a Long Way: Energy-Efficient, Accurate Conversion from Convolutional Neural Networks to Spiking Neural Networks.” has been accepted by Frontiers in Neuroscience 2022!!
(05/2022) As we celebrate the official opening of the Digital Innovation Facility, congratrulation to Mr. Wei Huang, telling us about the research he undertakes at the homepage of the University of Liverpool. (link)
(05/2022) Our new laboratory in Digital Innovation Facility officially opened!
(03/2022) Congratulations to Gaojie, whose paper on “Enhancing Adversarial Training with Second-Order Statistics of Weights” was accepted to CVPR.

2021

(09/2021) Workshop on Safety Assurance for Deep Learning in Underwater Robotics (Link)
(07/2021) Congratulations to Wei, who is one of the winners of the SIEMENSE AI-DA challenge, which concerns how to assess the dependability of machine learning models. Specifically, he won the “most original approach” award . There were 32 teams from 15 countries participated in this challenge. This work also won the best paper award in AISafety2021, paper is available.

2020

(10/2020) SOLITUDE project kick-off meeting
(10/2020) FOCETA project kick-off meeting
(07/2020) Trustworthy ACPS Lab website Launched