Efficient and Transferable Adversarial Examples from Bayesian Neural Networks
arXiv:2011.05074
Abstract
An established way to improve the transferability of black-box evasion attacks is to craft the adversarial examples on an ensemble-based surrogate to increase diversity. We argue that transferability is fundamentally related to uncertainty. Based on a state-of-the-art Bayesian Deep Learning technique, we propose a new method to efficiently build a surrogate by sampling approximately from the posterior distribution of neural network weights, which represents the belief about the value of each parameter. Our extensive experiments on ImageNet, CIFAR-10 and MNIST show that our approach improves the success rates of four state-of-the-art attacks significantly (up to 83.2 percentage points), in both intra-architecture and inter-architecture transferability. On ImageNet, our approach can reach 94% of success rate while reducing training computations from 11.6 to 2.4 exaflops, compared to an ensemble of independently trained DNNs. Our vanilla surrogate achieves 87.5% of the time higher transferability than three test-time techniques designed for this purpose. Our work demonstrates that the way to train a surrogate has been overlooked, although it is an important element of transfer-based attacks. We are, therefore, the first to review the effectiveness of several training methods in increasing transferability. We provide new directions to better understand the transferability phenomenon and offer a simple but strong baseline for future work.
arXiv commentAccepted at UAI 2022
References in corpus (13)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Explaining and Harnessing Adversarial Examples
- Intriguing properties of neural networks
- Delving into Transferable Adversarial Examples and Black-box Attacks
- Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
- Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets
- Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
- Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning
- Enhancing Adversarial Example Transferability with an Intermediate Level Attack
- Adversarial Distillation of Bayesian Neural Network Posteriors
- Robustness of Bayesian Neural Networks to Gradient-Based Attacks
- The Limitations of Model Uncertainty in Adversarial Settings
- Scalable Natural Gradient Langevin Dynamics in Practice