AdvHaze: Adversarial Haze Attack

Abstract

In recent years, adversarial attacks have drawn more attention for their value on evaluating and improving the robustness of machine learning models, especially, neural network models. However, previous attack methods have mainly focused on applying some $l^p$ norm-bounded noise perturbations. In this paper, we instead introduce a novel adversarial attack method based on haze, which is a common phenomenon in real-world scenery. Our method can synthesize potentially adversarial haze into an image based on the atmospheric scattering model with high realisticity and mislead classifiers to predict an incorrect class. We launch experiments on two popular datasets, i.e., ImageNet and NIPS~2017. We demonstrate that the proposed method achieves a high success rate, and holds better transferability across different classification models than the baselines. We also visualize the correlation matrices, which inspire us to jointly apply different perturbations to improve the success rate of the attack. We hope this work can boost the development of non-noise-based adversarial attacks and help evaluate and improve the robustness of DNNs.

References in corpus (4)

• Toward Multimodal Image-to-Image Translation
• U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
• Unrestricted Adversarial Examples via Semantic Manipulation
• Watch out! Motion is Blurring the Vision of Your Deep Neural Networks

Cited by in corpus (8)

• FakeTagger: Robust Safeguards against DeepFake Dissemination via Provenance Tracking
• AVA: Adversarial Vignetting Attack against Visual Recognition
• Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection
• Adversarial Relighting Against Face Recognition
• Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network
• ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networks
• AdvFilter: Predictive Perturbation-aware Filtering against Adversarial Attack via Multi-domain Learning
• Benchmarking Shadow Removal for Facial Landmark Detection and Beyond