An adversarial sample defense model based on computer attention mechanism
Authors:
- 14 May 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 665-673
Abstract
The traditional neural network can not realize the invariance of image rotation and distortion well, so the attacker can cheat the neural network by adding tiny disturbance on the image. If signposts are attacked, automatic driving will be misguided, leading to disastrous consequences. This paper proposes a new adversarial sample defense model based on attention mechanism, which used LSTM network to get the key features. Firstly, we describe our model which recognizes an object through enough main characteristics. It can discard large parts of the noise distributed throughout the image area. Secondly, we show recognition process of the model, receiving adversarial samples and then outputting the salient mask image which can be classified correctly by neural networks in deep learning. At last, we designed experiments to test model effect on the traffic sign and the general picture. The experimental results show that our defense model can strongly defend adversarial examples.Keywords
This publication has 13 references indexed in Scilit:
- A survey on adversarial attacks and defencesCAAI Transactions on Intelligence Technology, 2021
- Certified Robustness to Adversarial Examples with Differential Privacy2019
- Robust Physical-World Attacks on Deep Learning Visual Classification2018
- The Learned Inexact Project Gradient Descent Algorithm2018
- Adversarial image detection in deep neural networksMultimedia Tools and Applications, 2018
- Towards Evaluating the Robustness of Neural Networks2017
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks2016
- Learning temporal features using LSTM-CNN architecture for face anti-spoofing2015
- Vision-Based Traffic Sign Detection and Analysis for Intelligent Driver Assistance Systems: Perspectives and SurveyIEEE Transactions on Intelligent Transportation Systems, 2012
- Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognitionNeural Networks, 2012