paper-with-me

Papers

Provable robustness against all adversarial $l_p$-perturbations for $p\geq 1$

2019-05-27 · ICLR 2020 1 · Francesco Croce, Matthias Hein

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 $p\geq 1$.

📄 PDF Abstract BibTeX arXiv:1905.11213

Code (1)

fra31/mmr-universal 공식 구현 pytorch

Tasks

All

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Certifying Model Accuracy under Distribution Shifts

2022-01-28 · Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi

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…

model

On the Minimal Adversarial Perturbation for Deep Neural Networks with Provable Estimation Error

2022-01-04 · Fabio Brau, Giulio Rossolini, Alessandro Biondi, Giorgio Buttazzo

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

2022-02-02 · Mikhail Pautov, Olesya Kuznetsova, Nurislam Tursynbek, Aleksandr Petiushko 외

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 Learning

Certified Adversarial Robustness via Anisotropic Randomized Smoothing

2022-07-12 · Hanbin Hong, Yuan Hong

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 RobustnessAll

Abstract Gradient Training: A Unified Certification Framework for Data Poisoning, Unlearning, and Differential Privacy

2025-11-12 · Philip Sosnin, Matthew Wicker, Josh Collyer, Calvin Tsay arxiv

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