Towards Evaluating and Training Verifiably Robust Neural Networks

v1v2v3 (latest)

Towards Evaluating and Training Verifiably Robust Neural Networks

1 April 2021

Kehuan Zhang

ArXiv (abs)PDF HTML Github (17★)

Papers citing "Towards Evaluating and Training Verifiably Robust Neural Networks"

7 / 7 papers shown

Title
DeepBern-Nets: Taming the Complexity of Certifying Neural Networks using Bernstein Polynomial Activations and Precise Bound Propagation Haitham Khedr Yasser Shoukry 67 5 0 22 May 2023
Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity Andrew C. Cullen Paul Montague Shijie Liu S. Erfani Benjamin I. P. Rubinstein AAML 79 15 0 12 Oct 2022
IBP Regularization for Verified Adversarial Robustness via Branch-and-Bound Alessandro De Palma Rudy Bunel Krishnamurthy Dvijotham M. P. Kumar Robert Stanforth AAML 91 17 0 29 Jun 2022
Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions Marwan Omar Soohyeon Choi Daehun Nyang David A. Mohaisen 82 58 0 03 Jan 2022
Fast Certified Robust Training with Short Warmup Zhouxing Shi Yihan Wang Huan Zhang Jinfeng Yi Cho-Jui Hsieh AAML 107 57 0 31 Mar 2021
On the Paradox of Certified Training Nikola Jovanović Mislav Balunović Maximilian Baader Martin Vechev OOD 97 13 0 12 Feb 2021
SoK: Certified Robustness for Deep Neural Networks Linyi Li Tao Xie Yue Liu AAML 125 131 0 09 Sep 2020