A geometry-inspired decision-based attack
Deep neural networks have recently achieved tremendous success in image classification. Recent studies have however shown that they are easily misled into incorrect classification decisions by adversarial examples. Adversaries can even craft attacks by querying the model in black-box settings, where no information about the model is released except its final decision. Such decision-based attacks usually require lots of queries, while real-world image recognition systems might actually restrict the number of queries. In this paper, we propose qFool, a novel decision-based attack algorithm that can generate adversarial examples using a small number of queries. The qFool method can drastically reduce the number of queries compared to previous decision-based attacks while reaching the same quality of adversarial examples. We also enhance our method by constraining adversarial perturbations in low-frequency subspace, which can make qFool even more computationally efficient. Altogether, we manage to fool commercial image recognition systems with a small number of queries, which demonstrates the actual effectiveness of our new algorithm in practice.
Code (1)
Tasks
General Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples
Generating adversarial examples for natural language is hard, as natural language consists of discrete symbols, and examples are often of variable lengths. In this paper, we propose a geometry-inspired attack for generat…
Attack and defence in cellular decision-making: lessons from machine learning
Machine learning algorithms can be fooled by small well-designed adversarial perturbations. This is reminiscent of cellular decision-making where ligands (called antagonists) prevent correct signalling, like in early imm…
BIG-bench Machine LearningDecision MakingSparseFool: a few pixels make a big difference
Deep Neural Networks have achieved extraordinary results on image classification tasks, but have been shown to be vulnerable to attacks with carefully crafted perturbations of the input data. Although most attacks usuall…
image-classificationImage ClassificationStudying relationship between geometry of decision boundaries with network complexity for robustness analysis
Deep Neural networks are susceptible to adversarial attacks: if inputs are perturbed in a specific manner, it can result in misclassification. However, recent studies have shown that the robustness of the network has cer…
Tropical Decision Boundaries for Neural Networks Are Robust Against Adversarial Attacks
We introduce a simple, easy to implement, and computationally efficient tropical convolutional neural network architecture that is robust against adversarial attacks. We exploit the tropical nature of piece-wise linear n…