Min Wu
Interests
Artificial Intelligence Safety; Formal Methods.
Specifically, my research interests are (1) robustness guarantees for deep neural networks, (2) verification and testing of deep learning, and (3) explainable and interpretable machine learning.
Biography
I am a final year DPhil (PhD) Candidate under Prof. Marta Kwiatkowska at the Department of Computer Science, University of Oxford. I submitted my doctoral thesis titled "Robustness Evaluation of Deep Neural Networks with Provable Guarantees" in October 2019 and have passed the viva (oral examination) in February 2020.
Starting from October 2019, I have been a post-doctoral researcher in the same group, working on the explainability and interpretability of machine learning models for natural language processing.
Teaching
- 2019 - 2020 (HT): AIMS CDT Systems Verification, Teaching Assistant
- 2019 - 2020 (MT): Probabilistic Model Checking, Class Tutor
- 2018 - 2019 (MT): Probabilistic Model Checking, Class Tutor
- 2017 - 2018 (MT): Probabilistic Model Checking, Class Tutor
- 2016 - 2017 (MT): Probabilistic Model Checking, Practical Demonstrator
Selected Publications
-
A Game−Based Approximate Verification of Deep Neural Networks with Provable Guarantees
Min Wu‚ Matthew Wicker‚ Wenjie Ruan‚ Xiaowei Huang and Marta Kwiatkowska
In Theoretical Computer Science. Vol. 807. Pages 298−329. 2020.
In memory of Maurice Nivat‚ a founding father of Theoretical Computer Science − Part II
Details about A Game−Based Approximate Verification of Deep Neural Networks with Provable Guarantees | BibTeX data for A Game−Based Approximate Verification of Deep Neural Networks with Provable Guarantees | DOI (10.1016/j.tcs.2019.05.046) | Link to A Game−Based Approximate Verification of Deep Neural Networks with Provable Guarantees
-
Assessing Robustness of Text Classification through Maximal Safe Radius Computation
Emanuele LaMalfa‚ Min Wu‚ Luca Laurenti‚ Benjie Wang‚ Anthony Hartshorn and Marta Kwiatkowska
In Findings of the Association for Computational Linguistics: EMNLP 2020. Pages 2949–2968. Association for Computational Linguistics. 2020.
Details about Assessing Robustness of Text Classification through Maximal Safe Radius Computation | BibTeX data for Assessing Robustness of Text Classification through Maximal Safe Radius Computation | DOI (10.18653/v1/2020.findings-emnlp.266) | Link to Assessing Robustness of Text Classification through Maximal Safe Radius Computation
-
Robustness Guarantees for Deep Neural Networks on Videos
Min Wu and Marta Kwiatkowska
In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Pages 311−320. 2020.
Details about Robustness Guarantees for Deep Neural Networks on Videos | BibTeX data for Robustness Guarantees for Deep Neural Networks on Videos | DOI (10.1109/CVPR42600.2020.00039) | Link to Robustness Guarantees for Deep Neural Networks on Videos