Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$
In recent years several adversarial attacks and defenses have been proposed. Often seemingly robust models turn out to be non-robust when more sophisticated attacks are used. One way out of this dilemma are provable robustness guarantees. While provably robust models for specific $l_p$-perturbation models have been developed, we show that they do not come with any guarantee against other $l_q$-perturbations. We propose a new regularization scheme, MMR-Universal, for ReLU networks which enforces robustness wrt $l_1$- and $l_\infty$-perturbations and show how that leads to the first provably robust models wrt any $l_p$-norm for $p\geq 1$.
Code (1)
Tasks
AllMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Certifying Model Accuracy under Distribution Shifts
Certified robustness in machine learning has primarily focused on adversarial perturbations of the input with a fixed attack budget for each point in the data distribution. In this work, we present provable robustness gu…
modelOn the Minimal Adversarial Perturbation for Deep Neural Networks with Provable Estimation Error
Although Deep Neural Networks (DNNs) have shown incredible performance in perceptive and control tasks, several trustworthy issues are still open. One of the most discussed topics is the existence of adversarial perturba…
Smoothed Embeddings for Certified Few-Shot Learning
Randomized smoothing is considered to be the state-of-the-art provable defense against adversarial perturbations. However, it heavily exploits the fact that classifiers map input objects to class probabilities and do not…
Adversarial RobustnessFew-Shot LearningCertified Adversarial Robustness via Anisotropic Randomized Smoothing
Randomized smoothing has achieved great success for certified robustness against adversarial perturbations. Given any arbitrary classifier, randomized smoothing can guarantee the classifier's prediction over the perturbe…
Adversarial RobustnessAllAbstract Gradient Training: A Unified Certification Framework for Data Poisoning, Unlearning, and Differential Privacy
The impact of inference-time data perturbation (e.g., adversarial attacks) has been extensively studied in machine learning, leading to well-established certification techniques for adversarial robustness. In contrast, c…
Adversarial Robustness