Papers › Adversarial Training and Provable Defenses: Bridging the Gap

Adversarial Training and Provable Defenses: Bridging the Gap

1 May 2020ICLR 2020 1archive 2025-07-28

Mislav Balunovic, Martin Vechev

We present COLT, a new method to train neural networks based on a novel combination of adversarial training and provable defenses. The key idea is to model neural network training as a procedure which includes both, the verifier and the adversary. In every iteration, the verifier aims to certify the network using convex relaxation while the adversary tries to find inputs inside that convex relaxation which cause verification to fail. We experimentally show that this training method, named convex layerwise adversarial training (COLT), is promising and achieves the best of both worlds -- it produces a state-of-the-art neural network with certified robustness of 60.5% and accuracy of 78.4% on the challenging CIFAR-10 dataset with a 2/255 L-infinity perturbation. This significantly improves over the best concurrent results of 54.0% certified robustness and 71.5% accuracy.

PaperPDFCode

Code

eth-sri/colt officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections