Global Adversarial Robustness Guarantees for Neural Networks
We investigate global adversarial robustness guarantees for machine learning models. Specifically, given a trained model we consider the problem of computing the probability that its prediction at any point sampled from the (unknown) input distribution is susceptible to adversarial attacks. Assuming continuity of the model, we prove measurability for a selection of local robustness properties used in the literature. We then show how concentration inequalities can be employed to compute global robustness with estimation error upper-bounded by $\epsilon$, for any $\epsilon > 0$ selected a priori. We utilise the methods to provide statistically sound analysis of the robustness/accuracy trade-off for a variety of neural networks architectures and training methods on MNIST, Fashion-MNIST and CIFAR. We empirically observe that robustness and accuracy tend to be negatively correlated for networks trained via stochastic gradient descent and with iterative pruning techniques, while a positive trend is observed between them in Bayesian settings.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Probably Approximately Global Robustness Certification
We propose and investigate probabilistic guarantees for the adversarial robustness of classification algorithms. While traditional formal verification approaches for robustness are intractable and sampling-based approach…
Adversarial RobustnessGlobal Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the $L_0$ Norm
Deployment of deep neural networks (DNNs) in safety- or security-critical systems requires provable guarantees on their correct behaviour. A common requirement is robustness to adversarial perturbations in a neighbourhoo…
GPUProvable Adversarial Robustness for Fractional Lp Threat Models
In recent years, researchers have extensively studied adversarial robustness in a variety of threat models, including L_0, L_1, L_2, and L_infinity-norm bounded adversarial attacks. However, attacks bounded by fractional…
Adversarial RobustnessCertifying Global Robustness for Deep Neural Networks
A globally robust deep neural network resists perturbations on all meaningful inputs. Current robustness certification methods emphasize local robustness, struggling to scale and generalize. This paper presents a systema…
PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees
Point cloud classification is an essential component in many security-critical applications such as autonomous driving and augmented reality. However, point cloud classifiers are vulnerable to adversarially perturbed poi…
Autonomous DrivingClassificationPoint Cloud Classification