Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries

Abstract

We study adversarial examples in a black-box setting where the adversary only has API access to the target model and each query is expensive. Prior work on black-box adversarial examples follows one of two main strategies: (1) transfer attacks use white-box attacks on local models to find candidate adversarial examples that transfer to the target model, and (2) optimization-based attacks use queries to the target model and apply optimization techniques to search for adversarial examples. We propose hybrid attacks that combine both strategies, using candidate adversarial examples from local models as starting points for optimization-based attacks and using labels learned in optimization-based attacks to tune local models for finding transfer candidates. We empirically demonstrate on the MNIST, CIFAR10, and ImageNet datasets that our hybrid attack strategy reduces cost and improves success rates. We also introduce a seed prioritization strategy which enables attackers to focus their resources on the most promising seeds. Combining hybrid attacks with our seed prioritization strategy enables batch attacks that can reliably find adversarial examples with only a handful of queries.

arXiv commentUSENIX Security 2020 camera-ready version, Code available at: https://github.com/suyeecav/Hybrid-Attack

References in corpus (16)

• Ensemble Adversarial Training: Attacks and Defenses
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• Delving into Transferable Adversarial Examples and Black-box Attacks
• Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors
• Improving Black-box Adversarial Attacks with a Transfer-based Prior
• Simple Black-Box Adversarial Perturbations for Deep Networks
• Simple Black-box Adversarial Attacks
• Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attacks
• The Shattered Gradients Problem: If resnets are the answer, then what is the question?
• Exploring the Space of Black-box Attacks on Deep Neural Networks
• HopSkipJumpAttack: A Query-Efficient Decision-Based Attack
• Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization
• There are No Bit Parts for Sign Bits in Black-Box Attacks
• Query-limited Black-box Attacks to Classifiers
• Stateful Detection of Black-Box Adversarial Attacks

Cited by in corpus (3)

• RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit
• Black-box Adversarial Sample Generation Based on Differential Evolution
• Global Robustness Verification Networks