Certified Training: Small Boxes are All You Need
OPEN ACCESS
Author / Producer
Date
2023-02-01
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
To obtain, deterministic guarantees of adversarial robustness, specialized training methods are used. We propose, SABR, a novel such certified training method, based on the key insight that propagating interval bounds for a small but carefully selected subset of the adversarial input region is sufficient to approximate the worst-case loss over the whole region while significantly reducing approximation errors. We show in an extensive empirical evaluation that SABR outperforms existing certified defenses in terms of both standard and certifiable accuracies across perturbation magnitudes and datasets, pointing to a new class of certified training methods promising to alleviate the robustness-accuracy trade-off.
Permanent link
Publication status
published
External links
Editor
Book title
The Eleventh International Conference on Learning Representations
Journal / series
Volume
Pages / Article No.
Publisher
OpenReview
Event
11th International Conference on Learning Representations (ICLR 2023)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Certified Training; Certified Robustness; Adversarial Robustness; Robustness Verification
Organisational unit
03948 - Vechev, Martin / Vechev, Martin
Notes
Funding
101070617/22.00164 - European Lighthouse on Secure and Safe AI (SBFI)
MB22.00088 - SafeAI: Certified Safe, Fair and Robust Artificial Intelligence (SBFI)
MB22.00088 - SafeAI: Certified Safe, Fair and Robust Artificial Intelligence (SBFI)