Building Robust Deep Neural Networks for Road Sign Detection

12/26/2017
by   Arkar Min Aung, et al.
0

Deep Neural Networks are built to generalize outside of training set in mind by using techniques such as regularization, early stopping and dropout. But considerations to make them more resilient to adversarial examples are rarely taken. As deep neural networks become more prevalent in mission-critical and real-time systems, miscreants start to attack them by intentionally making deep neural networks to misclassify an object of one type to be seen as another type. This can be catastrophic in some scenarios where the classification of a deep neural network can lead to a fatal decision by a machine. In this work, we used GTSRB dataset to craft adversarial samples by Fast Gradient Sign Method and Jacobian Saliency Method, used those crafted adversarial samples to attack another Deep Convolutional Neural Network and built the attacked network to be more resilient against adversarial attacks by making it more robust by Defensive Distillation and Adversarial Training

READ FULL TEXT

page 3

page 4

page 5

page 6

page 7

page 8

research
04/20/2018

Learning More Robust Features with Adversarial Training

In recent years, it has been found that neural networks can be easily fo...
research
07/02/2020

Deep Learning Defenses Against Adversarial Examples for Dynamic Risk Assessment

Deep Neural Networks were first developed decades ago, but it was not un...
research
06/18/2021

Residual Error: a New Performance Measure for Adversarial Robustness

Despite the significant advances in deep learning over the past decade, ...
research
04/05/2018

Unifying Bilateral Filtering and Adversarial Training for Robust Neural Networks

Recent analysis of deep neural networks has revealed their vulnerability...
research
12/23/2021

Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization

Adversarial training (AT) has become a widely recognized defense mechani...
research
01/23/2019

Sitatapatra: Blocking the Transfer of Adversarial Samples

Convolutional Neural Networks (CNNs) are widely used to solve classifica...
research
10/27/2018

Regularization Effect of Fast Gradient Sign Method and its Generalization

Fast Gradient Sign Method (FSGM) is a popular method to generate adversa...

Please sign up or login with your details

Forgot password? Click here to reset