55 citations · 338 across the 26 of their papers we have counts for
26 papers
Leveraging System-Level Observations to Inform Bayesian Learning of Model Parameters for Quantitative Verification
Simos Gerasimou, Xingyu Zhao
Combining Bayesian learning and quantitative verification is a powerful toolset for analysing key quantitative properties of software systems, like reliability and response time. H…
On the Need for a Statistical Foundation in Scenario-Based Testing of Autonomous Vehicles
Xingyu Zhao, Robab Aghazadeh-Chakherlou, Chih-Hong Cheng +2
Scenario-based testing has emerged as a common method for autonomous vehicles (AVs) safety assessment, offering a more efficient alternative to mile-based testing by focusing on hi…
What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems
Saddek Bensalem, Chih-Hong Cheng, Wei Huang +3
Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges. Among the challenges, it…
Risk Controlled Image Retrieval
Kaiwen Cai, Chris Xiaoxuan Lu, Xingyu Zhao +1
Most image retrieval research prioritizes improving predictive performance, often overlooking situations where the reliability of predictions is equally important. The gap between…
A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation
Xiaowei Huang, Wenjie Ruan, Wei Huang +14
Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many…
Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT
Yi Qi, Xingyu Zhao, Siddartha Khastgir +1
Can safety analysis make use of Large Language Models (LLMs)? A case study explores Systems Theoretic Process Analysis (STPA) applied to Automatic Emergency Brake (AEB) and Electri…
Bayesian Learning for the Robust Verification of Autonomous Robots
Xingyu Zhao, Simos Gerasimou, Radu Calinescu +3
Autonomous robots used in infrastructure inspection, space exploration and other critical missions operate in highly dynamic environments. As such, they must continually verify the…
Decentralised and Cooperative Control of Multi-Robot Systems through Distributed Optimisation
Yi Dong, Zhongguo Li, Xingyu Zhao +2
Multi-robot cooperative control has gained extensive research interest due to its wide applications in civil, security, and military domains. This paper proposes a cooperative cont…
STPA for Learning-Enabled Systems: A Survey and A New Practice
Yi Qi, Yi Dong, Siddartha Khastgir +3
Systems Theoretic Process Analysis (STPA) is a systematic approach for hazard analysis that has been used across many industrial sectors including transportation, energy, and defen…
Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems
Yi Dong, Xingyu Zhao, Sen Wang +1
Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RAS). A key challenge to its deployment in real-life operations is the pre…
SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability
Wei Huang, Xingyu Zhao, Gaojie Jin +1
Interpretability of Deep Learning (DL) is a barrier to trustworthy AI. Despite great efforts made by the Explainable AI (XAI) community, explanations lack robustness -- indistingui…
Demonstrating Software Reliability using Possibly Correlated Tests: Insights from a Conservative Bayesian Approach
Kizito Salako, Xingyu Zhao
This paper presents Bayesian techniques for conservative claims about software reliability, particularly when evidence suggests the software's executions are not statistically inde…
Short-term Load Forecasting with Distributed Long Short-Term Memory
Yi Dong, Yang Chen, Xingyu Zhao +1
With the employment of smart meters, massive data on consumer behaviour can be collected by retailers. From the collected data, the retailers may obtain the household profile infor…
The Unnecessity of Assuming Statistically Independent Tests in Bayesian Software Reliability Assessments
Kizito Salako, Xingyu Zhao
When assessing a software-based system, the results of Bayesian statistical inference on operational testing data can provide strong support for software reliability claims. For in…
Hierarchical Distribution-Aware Testing of Deep Learning
Wei Huang, Xingyu Zhao, Alec Banks +2
Deep Learning (DL) is increasingly used in safety-critical applications, raising concerns about its reliability. DL suffers from a well-known problem of lacking robustness, especia…
Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance
Yi Dong, Wei Huang, Vibhav Bharti +6
The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) -- has resulted in the pressing need to assure th…
Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking
Yi Dong, Xingyu Zhao, Xiaowei Huang
While Deep Reinforcement Learning (DRL) provides transformational capabilities to the control of Robotics and Autonomous Systems (RAS), the black-box nature of DRL and uncertain de…
Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles
Xingyu Zhao, Wei Huang, Alec Banks +4
The utilisation of Deep Learning (DL) is advancing into increasingly more sophisticated applications. While it shows great potential to provide transformational capabilities, DL al…
Detecting Operational Adversarial Examples for Reliable Deep Learning
Xingyu Zhao, Wei Huang, Sven Schewe +2
The utilisation of Deep Learning (DL) raises new challenges regarding its dependability in critical applications. Sound verification and validation methods are needed to assure the…
BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations
Xingyu Zhao, Wei Huang, Xiaowei Huang +2
Given the pressing need for assuring algorithmic transparency, Explainable AI (XAI) has emerged as one of the key areas of AI research. In this paper, we develop a novel Bayesian e…
Embedding and Extraction of Knowledge in Tree Ensemble Classifiers
Wei Huang, Xingyu Zhao, Xiaowei Huang
The embedding and extraction of useful knowledge is a recent trend in machine learning applications, e.g., to supplement existing datasets that are small. Whilst, as the increasing…
Assessing Safety-Critical Systems from Operational Testing: A Study on Autonomous Vehicles
Xingyu Zhao, Kizito Salako, Lorenzo Strigini +2
Context: Demonstrating high reliability and safety for safety-critical systems (SCSs) remains a hard problem. Diverse evidence needs to be combined in a rigorous way: in particular…
A Safety Framework for Critical Systems Utilising Deep Neural Networks
Xingyu Zhao, Alec Banks, James Sharp +4
Increasingly sophisticated mathematical modelling processes from Machine Learning are being used to analyse complex data. However, the performance and explainability of these model…
Towards Integrating Formal Verification of Autonomous Robots with Battery Prognostics and Health Management
Xingyu Zhao, Matt Osborne, Jenny Lantair +6
The battery is a key component of autonomous robots. Its performance limits the robot's safety and reliability. Unlike liquid-fuel, a battery, as a chemical device, exhibits compli…