Enhancing Certified Robustness via Smoothed Weighted Ensembling

Abstract

Randomized smoothing has achieved state-of-the-art certified robustness against $l_2$-norm adversarial attacks. However, it is not wholly resolved on how to find the optimal base classifier for randomized smoothing. In this work, we employ a Smoothed WEighted ENsembling (SWEEN) scheme to improve the performance of randomized smoothed classifiers. We show the ensembling generality that SWEEN can help achieve optimal certified robustness. Furthermore, theoretical analysis proves that the optimal SWEEN model can be obtained from training under mild assumptions. We also develop an adaptive prediction algorithm to reduce the prediction and certification cost of SWEEN models. Extensive experiments show that SWEEN models outperform the upper envelope of their corresponding candidate models by a large margin. Moreover, SWEEN models constructed using a few small models can achieve comparable performance to a single large model with a notable reduction in training time.

References in corpus (29)

• Provable defenses against adversarial examples via the convex outer adversarial polytope
• Certified Adversarial Robustness via Randomized Smoothing
• Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
• On Evaluating Adversarial Robustness
• Certified Defenses against Adversarial Examples
• Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
• Efficient Neural Network Robustness Certification with General Activation Functions
• Evaluating Robustness of Neural Networks with Mixed Integer Programming
• On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
• Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
• An approach to reachability analysis for feed-forward ReLU neural networks
• Improving Adversarial Robustness via Promoting Ensemble Diversity
• Semidefinite relaxations for certifying robustness to adversarial examples
• Efficient Formal Safety Analysis of Neural Networks
• On Adaptive Attacks to Adversarial Example Defenses
• A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks
• Training verified learners with learned verifiers
• Ensemble Methods as a Defense to Adversarial Perturbations Against Deep Neural Networks
• MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius
• Provable Robustness of ReLU networks via Maximization of Linear Regions
• Deep Neural Networks as 0-1 Mixed Integer Linear Programs: A Feasibility Study
• Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers
• Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness
• Randomized Smoothing of All Shapes and Sizes
• Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework
• Random Smoothing Might be Unable to Certify ${\ell }_{\infty }$ Robustness for High-Dimensional Images
• EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attacks
• ATHENA: A Framework based on Diverse Weak Defenses for Building Adversarial Defense
• Adaptive Ensemble Prediction for Deep Neural Networks based on Confidence Level

Cited by in corpus (3)

• On the Certified Robustness for Ensemble Models and Beyond
• Improving Certified Robustness via Statistical Learning with Logical Reasoning
• Improving Adversarial Robustness via Unlabeled Out-of-Domain Data