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 Martin Vechev

Robustness Certification for Point Cloud Models


Mar 30, 2021
Tobias Lorenz, Anian Ruoss, Mislav Balunović, Gagandeep Singh, Martin Vechev


  Access Paper or Ask Questions

Precise Multi-Neuron Abstractions for Neural Network Certification


Mar 05, 2021
Mark Niklas Müller, Gleb Makarchuk, Gagandeep Singh, Markus Püschel, Martin Vechev


  Access Paper or Ask Questions

Automated Discovery of Adaptive Attacks on Adversarial Defenses


Feb 27, 2021
Chengyuan Yao, Pavol Bielik, Petar Tsankov, Martin Vechev

* 16 pages, 4 figures 

  Access Paper or Ask Questions

Certified Defenses: Why Tighter Relaxations May Hurt Training?


Feb 12, 2021
Nikola Jovanović, Mislav Balunović, Maximilian Baader, Martin Vechev


  Access Paper or Ask Questions

Efficient Certification of Spatial Robustness


Sep 19, 2020
Anian Ruoss, Maximilian Baader, Mislav Balunović, Martin Vechev


  Access Paper or Ask Questions

Scalable Inference of Symbolic Adversarial Examples


Jul 26, 2020
Dimitar I. Dimitrov, Gagandeep Singh, Timon Gehr, Martin Vechev


  Access Paper or Ask Questions

Neural Network Robustness Verification on GPUs


Jul 20, 2020
Christoph Müller, Gagandeep Singh, Markus Püschel, Martin Vechev


  Access Paper or Ask Questions

Fast and Effective Robustness Certification for Recurrent Neural Networks


May 27, 2020
Wonryong Ryou, Jiayu Chen, Mislav Balunovic, Gagandeep Singh, Andrei Dan, Martin Vechev


  Access Paper or Ask Questions

Robustness Certification of Generative Models


Apr 30, 2020
Matthew Mirman, Timon Gehr, Martin Vechev

* Prior version submitted to ICLR 2020 

  Access Paper or Ask Questions

Adversarial Attacks on Probabilistic Autoregressive Forecasting Models


Mar 08, 2020
Raphaël Dang-Nhu, Gagandeep Singh, Pavol Bielik, Martin Vechev

* 15 pages, 6 figures 

  Access Paper or Ask Questions

Certification of Semantic Perturbations via Randomized Smoothing


Feb 27, 2020
Marc Fischer, Maximilian Baader, Martin Vechev


  Access Paper or Ask Questions

Learning Certified Individually Fair Representations


Feb 24, 2020
Anian Ruoss, Mislav Balunović, Marc Fischer, Martin Vechev


  Access Paper or Ask Questions

Adversarial Robustness for Code


Feb 11, 2020
Pavol Bielik, Martin Vechev


  Access Paper or Ask Questions

Learning to Infer User Interface Attributes from Images


Dec 31, 2019
Philippe Schlattner, Pavol Bielik, Martin Vechev


  Access Paper or Ask Questions

Online Robustness Training for Deep Reinforcement Learning


Nov 22, 2019
Marc Fischer, Matthew Mirman, Steven Stalder, Martin Vechev


  Access Paper or Ask Questions

Universal Approximation with Certified Networks


Sep 30, 2019
Maximilian Baader, Matthew Mirman, Martin Vechev


  Access Paper or Ask Questions

A Provable Defense for Deep Residual Networks


Mar 29, 2019
Matthew Mirman, Gagandeep Singh, Martin Vechev


  Access Paper or Ask Questions

Learning a Static Analyzer from Data


Jun 25, 2017
Pavol Bielik, Veselin Raychev, Martin Vechev


  Access Paper or Ask Questions

Learning Disjunctions of Predicates


Jun 15, 2017
Nader H. Bshouty, Dana Drachsler-Cohen, Martin Vechev, Eran Yahav


  Access Paper or Ask Questions