Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Xiaowei Huang

Xiaowei Huang

University of Liverpool

Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles


Jun 02, 2021
Xingyu Zhao, Wei Huang, Alec Banks, Victoria Cox, David Flynn, Sven Schewe, Xiaowei Huang

* Accepted by the AISafety'21 Workshop at IJCAI-21. To appear in a volume of CEUR Workshop Proceedings 

  Access Paper or Ask Questions

Learning Robust Variational Information Bottleneck with Reference


Apr 29, 2021
Weizhu Qian, Bowei Chen, Xiaowei Huang

* 8 pages, 5 figures 

  Access Paper or Ask Questions

Detecting Operational Adversarial Examples for Reliable Deep Learning


Apr 16, 2021
Xingyu Zhao, Wei Huang, Sven Schewe, Yi Dong, Xiaowei Huang

* Preprint accepted by the fast abstract track of DSN'21 

  Access Paper or Ask Questions

A Little Energy Goes a Long Way: Energy-Efficient, Accurate Conversion from Convolutional Neural Networks to Spiking Neural Networks


Mar 06, 2021
Dengyu Wu, Xinping Yi, Xiaowei Huang


  Access Paper or Ask Questions

Abstraction and Symbolic Execution of Deep Neural Networks with Bayesian Approximation of Hidden Features


Mar 05, 2021
Nicolas Berthier, Amany Alshareef, James Sharp, Sven Schewe, Xiaowei Huang

* 38 pages, 10 figures 

  Access Paper or Ask Questions

BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations


Dec 05, 2020
Xingyu Zhao, Xiaowei Huang, Valentin Robu, David Flynn


  Access Paper or Ask Questions

Generalizing Universal Adversarial Attacks Beyond Additive Perturbations


Oct 29, 2020
Yanghao Zhang, Wenjie Ruan, Fu Wang, Xiaowei Huang

* A short version of this work will appear in the ICDM 2020 conference proceedings 

  Access Paper or Ask Questions

How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networks


Oct 17, 2020
Gaojie Jin, Xinping Yi, Liang Zhang, Lijun Zhang, Sven Schewe, Xiaowei Huang

* Accpeted by NeurIPS 2020 conference 

  Access Paper or Ask Questions

Formal Verification of Robustness and Resilience of Learning-Enabled State Estimation Systems for Robotics


Oct 16, 2020
Wei Huang, Yifan Zhou, Youcheng Sun, Alec Banks, Jie Meng, James Sharp, Simon Maskell, Xiaowei Huang


  Access Paper or Ask Questions

Embedding and Synthesis of Knowledge in Tree Ensemble Classifiers


Oct 16, 2020
Wei Huang, Xingyu Zhao, Xiaowei Huang


  Access Paper or Ask Questions

Towards the Quantification of Safety Risks in Deep Neural Networks


Sep 13, 2020
Peipei Xu, Wenjie Ruan, Xiaowei Huang

* 19 pages, 10 figures 

  Access Paper or Ask Questions

CasGCN: Predicting future cascade growth based on information diffusion graph


Sep 10, 2020
Zhixuan Xu, Minghui Qian, Xiaowei Huang, Jie Meng


  Access Paper or Ask Questions

Adaptable and Verifiable BDI Reasoning


Jul 23, 2020
Peter Stringer, Rafael C. Cardoso, Xiaowei Huang, Louise A. Dennis

* EPTCS 319, 2020, pp. 117-125 
* In Proceedings AREA 2020, arXiv:2007.11260 

  Access Paper or Ask Questions

Generating Adversarial Inputs Using A Black-box Differential Technique


Jul 10, 2020
João Batista Pereira Matos Juúnior, Lucas Carvalho Cordeiro, Marcelo d'Amorim, Xiaowei Huang


  Access Paper or Ask Questions

A Safety Framework for Critical Systems Utilising Deep Neural Networks


Mar 07, 2020
Xingyu Zhao, Alec Banks, James Sharp, Valentin Robu, David Flynn, Michael Fisher, Xiaowei Huang

* Submitted and under review 

  Access Paper or Ask Questions

Reliability Validation of Learning Enabled Vehicle Tracking


Feb 06, 2020
Youcheng Sun, Yifan Zhou, Simon Maskell, James Sharp, Xiaowei Huang


  Access Paper or Ask Questions

Test Metrics for Recurrent Neural Networks


Nov 05, 2019
Wei Huang, Youcheng Sun, James Sharp, Xiaowei Huang


  Access Paper or Ask Questions

Towards Integrating Formal Verification of Autonomous Robots with Battery Prognostics and Health Management


Aug 22, 2019
Xingyu Zhao, Matt Osborne, Jenny Lantair, Valentin Robu, David Flynn, Xiaowei Huang, Michael Fisher, Fabio Papacchini, Angelo Ferrando

* Proceedings of 17th International Conference on Software Engineering and Formal Methods (SEFM 2019), Oslo, Norway (September 2019) 

  Access Paper or Ask Questions

Explaining Deep Neural Networks Using Spectrum-Based Fault Localization


Aug 06, 2019
Youcheng Sun, Hana Chockler, Xiaowei Huang, Daniel Kroening


  Access Paper or Ask Questions

testRNN: Coverage-guided Testing on Recurrent Neural Networks


Jun 20, 2019
Wei Huang, Youcheng Sun, Xiaowei Huang, James Sharp

* Summited to ASE 2019 Demonstrations Track 

  Access Paper or Ask Questions

Analyzing Deep Neural Networks with Symbolic Propagation: Towards Higher Precision and Faster Verification


Feb 26, 2019
Pengfei Yang, Jiangchao Liu, Jianlin Li, Liqian Chen, Xiaowei Huang


  Access Paper or Ask Questions

Safety and Trustworthiness of Deep Neural Networks: A Survey


Jan 18, 2019
Xiaowei Huang, Daniel Kroening, Marta Kwiatkowska, Wenjie Ruan, Youcheng Sun, Emese Thamo, Min Wu, Xinping Yi

* The paper requires a significant upgrade, and since it could be completely different with its current version, we believe it is more suitable to withdraw 

  Access Paper or Ask Questions

Concolic Testing for Deep Neural Networks


Aug 04, 2018
Youcheng Sun, Min Wu, Wenjie Ruan, Xiaowei Huang, Marta Kwiatkowska, Daniel Kroening


  Access Paper or Ask Questions

A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees


Jul 10, 2018
Min Wu, Matthew Wicker, Wenjie Ruan, Xiaowei Huang, Marta Kwiatkowska


  Access Paper or Ask Questions

Reachability Analysis of Deep Neural Networks with Provable Guarantees


May 06, 2018
Wenjie Ruan, Xiaowei Huang, Marta Kwiatkowska

* This is the long version of the conference paper accepted in IJCAI-2018. Github: https://github.com/TrustAI/DeepGO 

  Access Paper or Ask Questions

Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for L0 Norm


Apr 16, 2018
Wenjie Ruan, Min Wu, Youcheng Sun, Xiaowei Huang, Daniel Kroening, Marta Kwiatkowska

* 39 Pages, Github: https://github.com/L0-TRE/L0-TRE 

  Access Paper or Ask Questions