DeepAI AI Chat
Log In Sign Up

Affine Disentangled GAN for Interpretable and Robust AV Perception

by   Letao Liu, et al.

Autonomous vehicles (AV) have progressed rapidly with the advancements in computer vision algorithms. The deep convolutional neural network as the main contributor to this advancement has boosted the classification accuracy dramatically. However, the discovery of adversarial examples reveals the generalization gap between dataset and the real world. Furthermore, affine transformations may also confuse computer vision based object detectors. The degradation of the perception system is undesirable for safety critical systems such as autonomous vehicles. In this paper, a deep learning system is proposed: Affine Disentangled GAN (ADIS-GAN), which is robust against affine transformations and adversarial attacks. It is demonstrated that conventional data augmentation for affine transformation and adversarial attacks are orthogonal, while ADIS-GAN can handle both attacks at the same time. Useful information such as image rotation angle and scaling factor are also generated in ADIS-GAN. On MNIST dataset, ADIS-GAN can achieve over 98 percent classification accuracy within 30 degrees rotation, and over 90 percent classification accuracy against FGSM and PGD adversarial attack.


page 1

page 2

page 4

page 5


Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehicles

In recent years, many deep learning models have been adopted in autonomo...

Improving Robustness of Adversarial Attacks Using an Affine-Invariant Gradient Estimator

Adversarial examples can deceive a deep neural network (DNN) by signific...

AdvRain: Adversarial Raindrops to Attack Camera-based Smart Vision Systems

Vision-based perception modules are increasingly deployed in many applic...

RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attacks

Capsule Networks (CapsNets) are able to hierarchically preserve the pose...

Minimizing Perceived Image Quality Loss Through Adversarial Attack Scoping

Neural networks are now actively being used for computer vision tasks in...

Rogue Signs: Deceiving Traffic Sign Recognition with Malicious Ads and Logos

We propose a new real-world attack against the computer vision based sys...

Dual affine moment invariants

Affine transformation is one of the most common transformations in natur...