Black-box Adversarial Attacks with Bayesian Optimization

Abstract

We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples using information limited to loss function evaluations of input-output pairs. We use Bayesian optimization~(BO) to specifically cater to scenarios involving low query budgets to develop query efficient adversarial attacks. We alleviate the issues surrounding BO in regards to optimizing high dimensional deep learning models by effective dimension upsampling techniques. Our proposed approach achieves performance comparable to the state of the art black-box adversarial attacks albeit with a much lower average query count. In particular, in low query budget regimes, our proposed method reduces the query count up to $80\%$ with respect to the state of the art methods.

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Auto-Encoding Variational Bayes
• Practical Bayesian Optimization of Machine Learning Algorithms
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• A Tutorial on Bayesian Optimization
• Query-Efficient Hard-label Black-box Attack:An Optimization-based Approach
• Practical Black-Box Attacks against Machine Learning
• HopSkipJumpAttack: A Query-Efficient Decision-Based Attack
• Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization
• Query-limited Black-box Attacks to Classifiers

Cited by in corpus (8)

• Adversarial Attacks on Graph Classification via Bayesian Optimisation
• CorrAttack: Black-box Adversarial Attack with Structured Search
• Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks
• Simulating Unknown Target Models for Query-Efficient Black-box Attacks
• Generating Adversarial Inputs Using A Black-box Differential Technique
• BO-DBA: Query-Efficient Decision-Based Adversarial Attacks via Bayesian Optimization
• AI-Powered GUI Attack and Its Defensive Methods
• Gaussian MRF Covariance Modeling for Efficient Black-Box Adversarial Attacks