Gradient-Free Adversarial Attacks for Bayesian Neural Networks
The existence of adversarial examples underscores the importance of understanding the robustness of machine learning models. Bayesian neural networks (BNNs), due to their calibrated uncertainty, have been shown to posses favorable adversarial robustness properties. However, when approximate Bayesian inference methods are employed, the adversarial robustness of BNNs is still not well understood. In this work, we employ gradient-free optimization methods in order to find adversarial examples for BNNs. In particular, we consider genetic algorithms, surrogate models, as well as zeroth order optimization methods and adapt them to the goal of finding adversarial examples for BNNs. In an empirical evaluation on the MNIST and Fashion MNIST datasets, we show that for various approximate Bayesian inference methods the usage of gradient-free algorithms can greatly improve the rate of finding adversarial examples compared to state-of-the-art gradient-based methods.
Code (1)
Tasks
Adversarial RobustnessBayesian InferenceSimilar Papers 제목 키워드 기반
On the Robustness of Bayesian Neural Networks to Adversarial Attacks
Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical and theoretical, training deep learning m…
Variational InferenceRobustness of Bayesian Neural Networks to Gradient-Based Attacks
Vulnerability to adversarial attacks is one of the principal hurdles to the adoption of deep learning in safety-critical applications. Despite significant efforts, both practical and theoretical, the problem remains open…
Variational InferenceEvasion Attacks Against Bayesian Predictive Models
There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has focused on studying weaknesses against …
Assessing the Adversarial Robustness of Monte Carlo and Distillation Methods for Deep Bayesian Neural Network Classification
In this paper, we consider the problem of assessing the adversarial robustness of deep neural network models under both Markov chain Monte Carlo (MCMC) and Bayesian Dark Knowledge (BDK) inference approximations. We chara…
Adversarial RobustnessGeneral ClassificationAdversarial EXEmples: Functionality-preserving Optimization of Adversarial Windows Malware
Windows malware classifiers that rely on static analysis have been proven vulnerable to adversarial EXEmples, i.e., malware samples carefully manipulated to evade detection. However, such attacks are typically optimized …