5 papers · 1 filter
Learning Better Certified Models from Empirically-Robust Teachers
Alessandro De Palma
Adversarial training attains strong empirical robustness to specific adversarial attacks by training on concrete adversarial perturbations, but it produces neural networks that are…
On Using Certified Training towards Empirical Robustness
Alessandro De Palma, Serge Durand, Zakaria Chihani +2
Adversarial training is arguably the most popular way to provide empirical robustness against specific adversarial examples. While variants based on multi-step attacks incur signif…
Verified Neural Compressed Sensing
Rudy Bunel, Krishnamurthy Dvijotham, M. Pawan Kumar +2
We develop the first (to the best of our knowledge) provably correct neural networks for a precise computational task, with the proof of correctness generated by an automated verif…
Expressive Losses for Verified Robustness via Convex Combinations
Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham +3
In order to train networks for verified adversarial robustness, it is common to over-approximate the worst-case loss over perturbation regions, resulting in networks that attain ve…
Scaling the Convex Barrier with Sparse Dual Algorithms
Alessandro De Palma, Harkirat Singh Behl, Rudy Bunel +2
Tight and efficient neural network bounding is crucial to the scaling of neural network verification systems. Many efficient bounding algorithms have been presented recently, but t…