AVA: Adversarial Vignetting Attack against Visual Recognition

Abstract

Vignetting is an inherited imaging phenomenon within almost all optical systems, showing as a radial intensity darkening toward the corners of an image. Since it is a common effect for photography and usually appears as a slight intensity variation, people usually regard it as a part of a photo and would not even want to post-process it. Due to this natural advantage, in this work, we study vignetting from a new viewpoint, i.e., adversarial vignetting attack (AVA), which aims to embed intentionally misleading information into vignetting and produce a natural adversarial example without noise patterns. This example can fool the state-of-the-art deep convolutional neural networks (CNNs) but is imperceptible to humans. To this end, we first propose the radial-isotropic adversarial vignetting attack (RI-AVA) based on the physical model of vignetting, where the physical parameters (e.g., illumination factor and focal length) are tuned through the guidance of target CNN models. To achieve higher transferability across different CNNs, we further propose radial-anisotropic adversarial vignetting attack (RA-AVA) by allowing the effective regions of vignetting to be radial-anisotropic and shape-free. Moreover, we propose the geometry-aware level-set optimization method to solve the adversarial vignetting regions and physical parameters jointly. We validate the proposed methods on three popular datasets, i.e., DEV, CIFAR10, and Tiny ImageNet, by attacking four CNNs, e.g., ResNet50, EfficientNet-B0, DenseNet121, and MobileNet-V2, demonstrating the advantages of our methods over baseline methods on both transferability and image quality.

arXiv commentThis work has been accepted to IJCAI2021

References in corpus (11)

• Deep Residual Learning for Image Recognition
• Densely Connected Convolutional Networks
• Unrestricted Adversarial Examples via Semantic Manipulation
• Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
• Boosting Adversarial Attacks with Momentum
• AdvHaze: Adversarial Haze Attack
• Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack
• Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection
• Bias Field Poses a Threat to DNN-based X-Ray Recognition
• Fooling LiDAR Perception via Adversarial Trajectory Perturbation
• DeepMix: Online Auto Data Augmentation for Robust Visual Object Tracking