Efficient Certification for Probabilistic Robustness
Recent developments on the robustness of neural networks have primarily emphasized the notion of worst-case adversarial robustness in both verification and robust training. However, often looser constraints are needed and some margin of error is allowed. We instead consider the task of probabilistic robustness, which assumes the input follows a known probabilistic distribution and seeks to bound the probability of a given network failing against the input. We focus on developing an efficient robustness verification algorithm by extending a bound-propagation-based approach. Our proposed algorithm improves upon the robustness certificate of this algorithm by up to $8\times$ while with no additional computational cost. In addition, we perform a case study on incorporating the probabilistic robustness verification during training for the first time.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
Certified but Fooled! Breaking Certified Defences with Ghost Certificates
Certified defenses promise provable robustness guarantees. We study the malicious exploitation of probabilistic certification frameworks to better understand the limits of guarantee provisions. Now, the objective is to n…
Adversarial Robustness Certification for Bayesian Neural Networks
We study the problem of certifying the robustness of Bayesian neural networks (BNNs) to adversarial input perturbations. Given a compact set of input points $T \subseteq \mathbb{R}^m$ and a set of output points $S \subse…
Adversarial RobustnessCollision AvoidanceregressionTraffic Sign RecognitionRisk-Averse Certification of Bayesian Neural Networks
In light of the inherently complex and dynamic nature of real-world environments, incorporating risk measures is crucial for the robustness evaluation of deep learning models. In this work, we propose a Risk-Averse Certi…
Regularized Training and Tight Certification for Randomized Smoothed Classifier with Provable Robustness
Recently smoothing deep neural network based classifiers via isotropic Gaussian perturbation is shown to be an effective and scalable way to provide state-of-the-art probabilistic robustness guarantee against $\ell_2$ no…
Probabilistic Stability Guarantees for Feature Attributions
Stability guarantees have emerged as a principled way to evaluate feature attributions, but existing certification methods rely on heavily smoothed classifiers and often produce conservative guarantees. To address these …