Job Search
I will be graduating in early 2022, and on the market for jobs. I'm open to research opportunities in either academia or industry, and happy to discuss freelancing and any potential big ideas you might have.Research Interests
Programming Language Design and Analysis, Machine Learning, AI Security, AI Safety, AI Trustworthiness, Program Synthesis, Computational Geometry, Formal Logic, ML Foundations.Publications
2022
The Fundamental Limits of Neural Networks for Interval Certified Robustness
Matthew Mirman, Maximilian Baader, Martin Vechev
TMLR
2022
2021
The Fundamental Limits of Interval Arithmetic for Neural Networks
Matthew Mirman, Maximilian Baader, Martin Vechev
arXiv
2021
Robustness Certification with Generative Models
Matthew Mirman, Alexander Hägele, Timon Gehr, Pavol Bielik, Martin Vechev
PLDI
2021
2020
Universal Approximation with Certified Networks
Maximilian Baader, Matthew Mirman, Martin Vechev
ICLR
2020
2019
Online Robustness Training for Deep Reinforcement Learning
Marc Fischer, Matthew Mirman, Steven Stalder, Martin Vechev
arXiv
2019
A Provable Defense for Deep Residual Networks
Matthew Mirman, Gagandeep Singh, Martin Vechev
ArXiv
2019
2018
Fast and Effective Robustness Certification
Gagandeep Singh, Timon Gehr, Matthew Mirman, Markus Püschel, Martin Vechev
NIPS
2018
Training Neural Machines with Trace-Based Supervision
Matthew Mirman, Dimitar Dimitrov, Pavle Djordjevich, Timon Gehr, Martin Vechev
ICML
2018
Differentiable Abstract Interpretation for Provably Robust Neural Networks
Matthew Mirman, Timon Gehr, Martin Vechev
ICML
2018
AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation
Timon Gehr, Matthew Mirman, Dana Drachsler-Cohen, Petar Tsankov, Swarat Chaudhuri, Martin Vechev
IEEE S&P
2018
Education
- ETH Zurich, January 2017 PhD Candidate in Computer Science
- CMU - SCS , August 2012 – May 2014 MSCS in Computer Science
- CMU - SCS , August 2009 – May 2012 BS in Computer Science