On Procedural Adversarial Noise Attack And Defense

Abstract

Deep Neural Networks (DNNs) are vulnerable to adversarial examples which would inveigle neural networks to make prediction errors with small perturbations on the input images. Researchers have been devoted to promoting the research on the universal adversarial perturbations (UAPs) which are gradient-free and have little prior knowledge on data distributions. Procedural adversarial noise attack is a data-free universal perturbation generation method. In this paper, we propose two universal adversarial perturbation (UAP) generation methods based on procedural noise functions: Simplex noise and Worley noise. In our framework, the shading which disturbs visual classification is generated with rendering technology. Without changing the semantic representations, the adversarial examples generated via our methods show superior performance on the attack.

arXiv commentRemove theoretical analysis and focus on the empirical study

References in corpus (14)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• On Evaluating Adversarial Robustness
• Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
• Shadow Detection: A Survey and Comparative Evaluation of Recent Methods
• Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
• Improving Adversarial Robustness via Promoting Ensemble Diversity
• Simple Black-box Adversarial Attacks
• Deep Defense: Training DNNs with Improved Adversarial Robustness
• Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimization
• NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks
• Adversarial Spheres
• Defending against Whitebox Adversarial Attacks via Randomized Discretization
• Revisiting Adversarial Risk
• Sensitivity of Deep Convolutional Networks to Gabor Noise