Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attacks
We consider adversarial examples for image classification in the black-box decision-based setting. Here, an attacker cannot access confidence scores, but only the final label. Most attacks for this scenario are either unreliable or inefficient. Focusing on the latter, we show that a specific class of attacks, Boundary Attacks, can be reinterpreted as a biased sampling framework that gains efficiency from domain knowledge. We identify three such biases, image frequency, regional masks and surrogate gradients, and evaluate their performance against an ImageNet classifier. We show that the combination of these biases outperforms the state of the art by a wide margin. We also showcase an efficient way to attack the Google Cloud Vision API, where we craft convincing perturbations with just a few hundred queries. Finally, the methods we propose have also been found to work very well against strong defenses: Our targeted attack won second place in the NeurIPS 2018 Adversarial Vision Challenge.
Code (3)
Tasks
image-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Improving LIME Robustness with Smarter Locality Sampling
Explainability algorithms such as LIME have enabled machine learning systems to adopt transparency and fairness, which are important qualities in commercial use cases. However, recent work has shown that LIME's naive sam…
FairnessGenerative Adversarial NetworkThe Bias-Expressivity Trade-off
Learning algorithms need bias to generalize and perform better than random guessing. We examine the flexibility (expressivity) of biased algorithms. An expressive algorithm can adapt to changing training data, altering i…
Query-Efficient Black-box Adversarial Attacks Guided by a Transfer-based Prior
Adversarial attacks have been extensively studied in recent years since they can identify the vulnerability of deep learning models before deployed. In this paper, we consider the black-box adversarial setting, where the…
Generative Deep Learning Techniques for Password Generation
Password guessing approaches via deep learning have recently been investigated with significant breakthroughs in their ability to generate novel, realistic password candidates. In the present work we study a broad collec…
Deep LearningGNPassGAN: Improved Generative Adversarial Networks For Trawling Offline Password Guessing
The security of passwords depends on a thorough understanding of the strategies used by attackers. Unfortunately, real-world adversaries use pragmatic guessing tactics like dictionary attacks, which are difficult to simu…