Universal Adversarial Perturbations: A Survey

Abstract

Over the past decade, Deep Learning has emerged as a useful and efficient tool to solve a wide variety of complex learning problems ranging from image classification to human pose estimation, which is challenging to solve using statistical machine learning algorithms. However, despite their superior performance, deep neural networks are susceptible to adversarial perturbations, which can cause the network's prediction to change without making perceptible changes to the input image, thus creating severe security issues at the time of deployment of such systems. Recent works have shown the existence of Universal Adversarial Perturbations, which, when added to any image in a dataset, misclassifies it when passed through a target model. Such perturbations are more practical to deploy since there is minimal computation done during the actual attack. Several techniques have also been proposed to defend the neural networks against these perturbations. In this paper, we attempt to provide a detailed discussion on the various data-driven and data-independent methods for generating universal perturbations, along with measures to defend against such perturbations. We also cover the applications of such universal perturbations in various deep learning tasks.

20 pages, 17 figures

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• YOLOv3: An Incremental Improvement
• Densely Connected Convolutional Networks
• Robust Physical-World Attacks on Deep Learning Models
• LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images
• Fast Feature Fool: A data independent approach to universal adversarial perturbations
• Playing the Game of Universal Adversarial Perturbations
• Analysis of Deep Networks for Monocular Depth Estimation Through Adversarial Attacks with Proposal of a Defense Method

Cited by in corpus (5)

• How adversarial attacks can disrupt seemingly stable accurate classifiers
• Decision-based Universal Adversarial Attack
• Resilience of Autonomous Vehicle Object Category Detection to Universal Adversarial Perturbations
• Verifying Integrity of Deep Ensemble Models by Lossless Black-box Watermarking with Sensitive Samples
• You Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries