SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
arXiv:1906.07927
Abstract
Deep neural networks (DNNs) have achieved great success in various applications due to their strong expressive power. However, recent studies have shown that DNNs are vulnerable to adversarial examples which are manipulated instances targeting to mislead DNNs to make incorrect predictions. Currently, most such adversarial examples try to guarantee "subtle perturbation" by limiting the norm of the perturbation. In this paper, we aim to explore the impact of semantic manipulation on DNNs predictions by manipulating the semantic attributes of images and generate "unrestricted adversarial examples". In particular, we propose an algorithm \emph{SemanticAdv} which leverages disentangled semantic factors to generate adversarial perturbation by altering controlled semantic attributes to fool the learner towards various "adversarial" targets. We conduct extensive experiments to show that the semantic based adversarial examples can not only fool different learning tasks such as face verification and landmark detection, but also achieve high targeted attack success rate against \emph{real-world black-box} services such as Azure face verification service based on transferability. To further demonstrate the applicability of \emph{SemanticAdv} beyond face recognition domain, we also generate semantic perturbations on street-view images. Such adversarial examples with controlled semantic manipulation can shed light on further understanding about vulnerabilities of DNNs as well as potential defensive approaches.
arXiv commentTo appear at ECCV 2020
References in corpus (22)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Auto-Encoding Variational Bayes
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Generative Adversarial Text to Image Synthesis
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Conditional Image Generation with PixelCNN Decoders
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- Pixel Recurrent Neural Networks
- A study of the effect of JPG compression on adversarial images
- Spatially Transformed Adversarial Examples
- Better Mixing via Deep Representations
- GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
- Houdini: Fooling Deep Structured Prediction Models
- Generative Visual Manipulation on the Natural Image Manifold
- Generative Face Completion
- Testing Robustness Against Unforeseen Adversaries
- Unrestricted Adversarial Examples
- Learning Hierarchical Semantic Image Manipulation through Structured Representations
- Unrestricted Adversarial Examples via Semantic Manipulation
- Wasserstein Adversarial Examples via Projected Sinkhorn Iterations
- Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation
- Neural Face Editing with Intrinsic Image Disentangling