Dr Xingyu Zhao PhD

Lecturer Computer Science

Work email Xingyu.Zhao@liverpool.ac.uk
Personal Websitehttps://www.xzhao.me/

Publications

Selected Publications

BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations (Conference Paper - 2020)
Interval Change-Point Detection for Runtime Probabilistic Model Checking (Conference Paper - 2020)
Assessing safety-critical systems from operational testing: A study on autonomous vehicles (Journal article - 2020)
Probabilistic Model Checking of Robots Deployed in Extreme Environments (Conference Paper - 2018)
A Safety Framework for Critical Systems Utilising Deep Neural Networks (Conference Paper - 2020)

Filter the publication list

Filter list by type

Show all
Journal article
Conference paper
Chapter
Other

2024

Demonstrating software reliability using possibly correlated tests: Insights from a conservative Bayesian approach (Journal article)

Salako, K., & Zhao, X. (2024). Demonstrating software reliability using possibly correlated tests: Insights from a conservative Bayesian approach. Quality and Reliability Engineering International, 40(3), 1197-1220. doi:10.1002/qre.3460

DOI: 10.1002/qre.3460

Representation-Based Robustness in Goal-Conditioned Reinforcement Learning (Conference Paper)

Yin, X., Wu, S., Liu, J., Fang, M., Zhao, X., Huang, X., & Ruan, W. (n.d.). Representation-Based Robustness in Goal-Conditioned Reinforcement Learning. In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 38 (pp. 21761-21769). Association for the Advancement of Artificial Intelligence (AAAI). doi:10.1609/aaai.v38i19.30176

DOI: 10.1609/aaai.v38i19.30176

Hierarchical Distribution-aware Testing of Deep Learning (Journal article)

Huang, W., Zhao, X., Banks, A., Cox, V., & Huang, X. (2024). Hierarchical Distribution-aware Testing of Deep Learning. ACM Transactions on Software Engineering and Methodology, 33(2), 1-35. doi:10.1145/3625290

DOI: 10.1145/3625290

ProTIP: Probabilistic Robustness Verification on Text-to-Image Diffusion Models against Stochastic Perturbation (Preprint)

Instance-Level Safety-Aware Fidelity of Synthetic Data and Its Calibration (Preprint)

Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems (Journal article)

Dong, Y., Zhao, X., Wang, S., & Huang, X. (2024). Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems. IEEE Robotics and Automation Letters, 1-8. doi:10.1109/lra.2024.3364471

DOI: 10.1109/lra.2024.3364471

Building Guardrails for Large Language Models (Preprint)

Bridging formal methods and machine learning with model checking and global optimisation (Journal article)

Bensalem, S., Huang, X., Ruan, W., Tang, Q., Wu, C., & Zhao, X. (2024). Bridging formal methods and machine learning with model checking and global optimisation. Journal of Logical and Algebraic Methods in Programming, 137, 100941. doi:10.1016/j.jlamp.2023.100941

DOI: 10.1016/j.jlamp.2023.100941

Bayesian learning for the robust verification of autonomous robots (Journal article)

Zhao, X., Gerasimou, S., Calinescu, R., Imrie, C., Robu, V., & Flynn, D. (n.d.). Bayesian learning for the robust verification of autonomous robots. Communications Engineering, 3(1). doi:10.1038/s44172-024-00162-y

DOI: 10.1038/s44172-024-00162-y

What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety-Critical Systems (Conference Paper)

Bensalem, S., Cheng, C. -H., Huang, W., Huang, X., Wu, C., & Zhao, X. (2024). What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety-Critical Systems. In Unknown Conference (pp. 55-76). Springer Nature Switzerland. doi:10.1007/978-3-031-46002-9_4

DOI: 10.1007/978-3-031-46002-9_4

2023

ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learning (Preprint)

Cycle-Consistent Generative Adversarial Network Architectures for Audio Visual Speech Recognition (Conference Paper)

He, Y., Seng, K. P., Ang, L. -M., & Zhao, X. (2023). Cycle-Consistent Generative Adversarial Network Architectures for Audio Visual Speech Recognition. In 2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC). IEEE. doi:10.1109/icspcc59353.2023.10400358

DOI: 10.1109/icspcc59353.2023.10400358

SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability (Conference Paper)

Huang, W., Zhao, X., Jin, G., & Huang, X. (2023). SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability. In 2023 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE. doi:10.1109/iccv51070.2023.00190

DOI: 10.1109/iccv51070.2023.00190

STPA for Learning-Enabled Systems: A Survey and A New Practice (Conference Paper)

Qi, Y., Dong, Y., Khastgir, S., Jennings, P., Zhao, X., & Huang, X. (2023). STPA for Learning-Enabled Systems: A Survey and A New Practice. In 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC). IEEE. doi:10.1109/itsc57777.2023.10422520

DOI: 10.1109/itsc57777.2023.10422520

The Impact of Live Polling Quizzes on Student Engagement and Performance in Computer Science Lectures (Preprint)

What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems (Preprint)

Risk Controlled Image Retrieval (Preprint)

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

Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT (Preprint)

Short-term Load Forecasting with Distributed Long Short-Term Memory (Conference Paper)

Dong, Y., Chen, Y., Zhao, X., & Huang, X. (2023). Short-term Load Forecasting with Distributed Long Short-Term Memory. In 2023 IEEE POWER & ENERGY SOCIETY INNOVATIVE SMART GRID TECHNOLOGIES CONFERENCE, ISGT. doi:10.1109/ISGT51731.2023.10066368

DOI: 10.1109/ISGT51731.2023.10066368

Bayesian Learning for the Robust Verification of Autonomous Robots (Preprint)

STPA for Learning-Enabled Systems: A Survey and A New Practice (Preprint)

Decentralised and Cooperative Control of Multi-Robot Systems through Distributed Optimisation (Preprint)

The Unnecessity of Assuming Statistically Independent Tests in Bayesian Software Reliability Assessments (Journal article)

Salako, K., & Zhao, X. (2023). The Unnecessity of Assuming Statistically Independent Tests in Bayesian Software Reliability Assessments. IEEE Transactions on Software Engineering, 1-9. doi:10.1109/tse.2022.3233802

Decentralised and Cooperative Control of Multi-Robot Systems through Distributed Optimisation (Conference Paper)

Dong, Y., Li, Z., Zhao, X., Ding, Z., & Huang, X. (2023). Decentralised and Cooperative Control of Multi-Robot Systems through Distributed Optimisation. In Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS Vol. 2023-May (pp. 1421-1429).

2022

Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems (Preprint)

Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking (Conference Paper)

Dong, Y., Zhao, X., & Huang, X. (2022). Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking. In 2022 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (pp. 5171-5178). doi:10.1109/IROS47612.2022.9981794

DOI: 10.1109/IROS47612.2022.9981794

Dependable learning-enabled multiagent systems (Journal article)

Huang, X., Peng, B., & Zhao, X. (2022). Dependable learning-enabled multiagent systems. AI COMMUNICATIONS, 35(4), 407-420. doi:10.3233/AIC-220128

DOI: 10.3233/AIC-220128

SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability (Preprint)

Demonstrating Software Reliability using Possibly Correlated Tests: Insights from a Conservative Bayesian Approach (Preprint)

The Unnecessity of Assuming Statistically Independent Tests in Bayesian Software Reliability Assessments (Preprint)

DOI: 10.48550/arxiv.2208.00462

Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking (Conference Paper)

Dong, Y., Zhao, X., & Huang, X. (2021). Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking. Retrieved from http://dx.doi.org/10.1109/IROS47612.2022.9981794

Hierarchical Distribution-Aware Testing of Deep Learning (Preprint)

A Hierarchical HAZOP-Like Safety Analysis for Learning-Enabled Systems (Conference Paper)

Qi, Y., Conmy, P. R., Huang, W., Zhao, X., & Huang, X. (2022). A Hierarchical HAZOP-Like Safety Analysis for Learning-Enabled Systems. In CEUR Workshop Proceedings Vol. 3215.

Bridging Formal Methods and Machine Learning with Global Optimisation (Chapter)

Huang, X., Ruan, W., Tang, Q., & Zhao, X. (2022). Bridging Formal Methods and Machine Learning with Global Optimisation. In Formal Methods and Software Engineering (pp. 1-19). Springer International Publishing. doi:10.1007/978-3-031-17244-1_1

DOI: 10.1007/978-3-031-17244-1_1

2021

Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance (Preprint)

DOI: 10.48550/arxiv.2112.00646

Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance (Journal article)

Dong, Y., Huang, W., Bharti, V., Cox, V., Banks, A., Wang, S., . . . Huang, X. (2023). Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance. ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS, 22(3). doi:10.1145/3570918

Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles (Conference Paper)

Zhao, X., Huang, W., Banks, A., Cox, V., Flynn, D., Schewe, S., & Huang, X. (2021). Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles. Retrieved from http://arxiv.org/abs/2106.01258v1

Conservative Confidence Bounds in Safety, from Generalised Claims of Improvement Statistical Evidence (Conference Paper)

Salako, K., Strigini, L., & Zhao, X. (2021). Conservative Confidence Bounds in Safety, from Generalised Claims of Improvement & Statistical Evidence. In 51ST ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS (DSN 2021) (pp. 451-462). doi:10.1109/DSN48987.2021.00055

DOI: 10.1109/DSN48987.2021.00055

Coverage Guided Testing for Recurrent Neural Networks (Journal article)

Huang, W., Sun, Y., Zhao, X., Sharp, J., Ruan, W., Meng, J., & Huang, X. (n.d.). Coverage Guided Testing for Recurrent Neural Networks. IEEE Transactions on Reliability.

Detecting Operational Adversarial Examples for Reliable Deep Learning (Conference Paper)

Zhao, X., Huang, W., Schewe, S., Dong, Y., & Huang, X. (2021). Detecting Operational Adversarial Examples for Reliable Deep Learning. In 51ST ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS - SUPPLEMENTAL VOL (DSN 2021) (pp. 5-6). doi:10.1109/DSN-S52858.2021.00013

DOI: 10.1109/DSN-S52858.2021.00013

BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations (Conference Paper)

Zhao, X., Huang, W., Huang, X., Robu, V., & Flynn, D. (2021). BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations. In Proceedings of Machine Learning Research Vol. 161 (pp. 408-418).

2020

Interval Change-Point Detection for Runtime Probabilistic Model Checking (Conference Paper)

Zhao, X., Calinescu, R., Gerasimou, S., Robu, V., & Flynn, D. (2020). Interval Change-Point Detection for Runtime Probabilistic Model Checking. In 2020 35TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING (ASE 2020) (pp. 163-174). doi:10.1145/3324884.3416565

DOI: 10.1145/3324884.3416565

BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations (Conference Paper)

Zhao, X., Huang, W., Huang, X., Robu, V., & Flynn, D. (2020). BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations. Retrieved from http://arxiv.org/abs/2012.03058v5

Embedding and Extraction of Knowledge in Tree Ensemble Classifiers (Journal article)

Huang, W., Zhao, X., & Huang, X. (n.d.). Embedding and Extraction of Knowledge in Tree Ensemble Classifiers. Machine Learning. Retrieved from http://arxiv.org/abs/2010.08281v2

Assessing safety-critical systems from operational testing: A study on autonomous vehicles (Journal article)

Zhao, X., Salako, K., Strigini, L., Robu, V., & Flynn, D. (2020). Assessing safety-critical systems from operational testing: A study on autonomous vehicles. INFORMATION AND SOFTWARE TECHNOLOGY, 128. doi:10.1016/j.infsof.2020.106393

DOI: 10.1016/j.infsof.2020.106393

On reliability assessment when a software-based system is replaced by a thought-to-be-better one (Journal article)

Littlewood, B., Salako, K., Strigini, L., & Zhao, X. (2020). On reliability assessment when a software-based system is replaced by a thought-to-be-better one. RELIABILITY ENGINEERING & SYSTEM SAFETY, 197. doi:10.1016/j.ress.2019.106752

DOI: 10.1016/j.ress.2019.106752

A Safety Framework for Critical Systems Utilising Deep Neural Networks (Preprint)

DOI: 10.48550/arxiv.2003.05311

A Safety Framework for Critical Systems Utilising Deep Neural Networks (Conference Paper)

Zhao, X., Banks, A., Sharp, J., Robu, V., Flynn, D., Fisher, M., & Huang, X. (2020). A Safety Framework for Critical Systems Utilising Deep Neural Networks. Retrieved from http://dx.doi.org/10.1007/978-3-030-54549-9_16

2019

Coverage-Guided Testing for Recurrent Neural Networks (Journal article)

Huang, W., Sun, Y., Zhao, X., Sharp, J., Ruan, W., Meng, J., & Huang, X. (2022). Coverage-Guided Testing for Recurrent Neural Networks. IEEE TRANSACTIONS ON RELIABILITY, 71(3), 1191-1206. doi:10.1109/TR.2021.3080664

DOI: 10.1109/TR.2021.3080664

UAS Operators Safety and Reliability Survey: Emerging Technologies towards the Certification of Autonomous UAS (Conference Paper)

Osborne, M., Lantair, J., Shafiq, Z., Zhao, X., Robu, V., Flynn, D., & Perry, J. (2019). UAS Operators Safety and Reliability Survey: Emerging Technologies towards the Certification of Autonomous UAS. In 2019 4TH INTERNATIONAL CONFERENCE ON SYSTEM RELIABILITY AND SAFETY (ICSRS 2019) (pp. 203-212). doi:10.1109/icsrs48664.2019.8987692

DOI: 10.1109/icsrs48664.2019.8987692

The Application of Machine Learning and Low Frequency Sonar for Subsea Power Cable Integrity Evaluation (Conference Paper)

Tang, W., Flynn, D., Brown, K., Valentin, R., & Zhao, X. (2019). The Application of Machine Learning and Low Frequency Sonar for Subsea Power Cable Integrity Evaluation. In OCEANS 2019 MTS/IEEE SEATTLE. Retrieved from https://www.webofscience.com/

The Design of a Fusion Prognostic Model and Health Management System for Subsea Power Cables (Conference Paper)

Tang, W., Flynn, D., Brown, K., Valentin, R., & Zhao, X. (2019). The Design of a Fusion Prognostic Model and Health Management System for Subsea Power Cables. In OCEANS 2019 MTS/IEEE SEATTLE. Retrieved from https://www.webofscience.com/

Towards Integrating Formal Verification of Autonomous Robots with Battery Prognostics and Health Management (Conference Paper)

Zhao, X., Osborne, M., Lantair, J., Robu, V., Flynn, D., Huang, X., . . . Ferrando, A. (2019). Towards Integrating Formal Verification of Autonomous Robots with Battery Prognostics and Health Management. In SOFTWARE ENGINEERING AND FORMAL METHODS (SEFM 2019) Vol. 11724 (pp. 105-124). doi:10.1007/978-3-030-30446-1_6

DOI: 10.1007/978-3-030-30446-1_6

Assessing the Safety and Reliability of Autonomous Vehicles from Road Testing (Conference Paper)

Zhao, X., Robu, V., Flynn, D., Salako, K., & Strigini, L. (2019). Assessing the Safety and Reliability of Autonomous Vehicles from Road Testing. In 2019 IEEE 30TH INTERNATIONAL SYMPOSIUM ON SOFTWARE RELIABILITY ENGINEERING (ISSRE) (pp. 13-23). doi:10.1109/ISSRE.2019.00012

DOI: 10.1109/ISSRE.2019.00012

Machine learning methods for wind turbine condition monitoring: A review (Journal article)

Stetco, A., Dinmohammadi, F., Zhao, X., Robu, V., Flynn, D., Barnes, M., . . . Nenadic, G. (2019). Machine learning methods for wind turbine condition monitoring: A review. RENEWABLE ENERGY, 133, 620-635. doi:10.1016/j.renene.2018.10.047

DOI: 10.1016/j.renene.2018.10.047

2018

Probabilistic Model Checking of Robots Deployed in Extreme Environments (Conference Paper)

Zhao, X., Robu, V., Flynn, D., Dinmohammadi, F., Fisher, M., & Webster, M. (2019). Probabilistic Model Checking of Robots Deployed in Extreme Environments. In THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE (pp. 8066-8074). Retrieved from https://www.webofscience.com/

Verifiable Self-Certifying Autonomous Systems (Conference Paper)

Fisher, M., Collins, E., Dennis, L., Luckcuck, M., Webster, M., Jump, M., . . . Zhao, X. (2018). Verifiable Self-Certifying Autonomous Systems. In 2018 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW). IEEE. doi:10.1109/issrew.2018.00028

DOI: 10.1109/issrew.2018.00028

Conservative claims for the probability of perfection of a software-based system using operational experience of previous similar systems (Journal article)

Zhao, X., Littlewood, B., Povyakalo, A., Strigini, L., & Wright, D. (2018). Conservative claims for the probability of perfection of a software-based system using operational experience of previous similar systems. RELIABILITY ENGINEERING & SYSTEM SAFETY, 175, 265-282. doi:10.1016/j.ress.2018.03.032

DOI: 10.1016/j.ress.2018.03.032

2017

Modeling the probability of failure on demand (<i>pfd</i>) of a 1-out-of-2 system in which one channel is "quasi-perfect" (Journal article)

Zhao, X., Littlewood, B., Povyakalo, A., Strigini, L., & Wright, D. (2017). Modeling the probability of failure on demand (<i>pfd</i>) of a 1-out-of-2 system in which one channel is "quasi-perfect". RELIABILITY ENGINEERING & SYSTEM SAFETY, 158, 230-245. doi:10.1016/j.ress.2016.09.002

DOI: 10.1016/j.ress.2016.09.002

2016

Conservative Claims about the Probability of Perfection of Software-based Systems (Conference Paper)

Zhao, X., Littlewood, B., Povyakalo, A., & Wright, D. (2015). Conservative Claims about the Probability of Perfection of Software-based Systems. In 2015 IEEE 26TH INTERNATIONAL SYMPOSIUM ON SOFTWARE RELIABILITY ENGINEERING (ISSRE) (pp. 130-140). Retrieved from https://www.webofscience.com/

2014

A Dependability Case Construction Approach Based on Dependability Deviation Analysis (Journal article)

Zhang, D. J., Lu, M. Y., & Zhao, X. Y. (n.d.). A Dependability Case Construction Approach Based on Dependability Deviation Analysis. Applied Mechanics and Materials, 543-547, 3682-3687. doi:10.4028/www.scientific.net/amm.543-547.3682

DOI: 10.4028/www.scientific.net/amm.543-547.3682

2012

A New Approach to Assessment of Confidence in Assurance Cases (Conference Paper)

Zhao, X., Zhang, D., Lu, M., & Zeng, F. (2012). A New Approach to Assessment of Confidence in Assurance Cases. In Unknown Conference (pp. 79-91). Springer Berlin Heidelberg. doi:10.1007/978-3-642-33675-1_7

DOI: 10.1007/978-3-642-33675-1_7

2011

Variance Analysis Based Software Fault Localization (Conference Paper)

Variance Analysis Based Software Fault Localization (2011). In Unknown Conference (pp. 333-339). ASME Press. doi:10.1115/1.859858.paper46

DOI: 10.1115/1.859858.paper46