Bio-inspired Robustness: A Review

03/16/2021
by   Harshitha Machiraju, et al.
9

Deep convolutional neural networks (DCNNs) have revolutionized computer vision and are often advocated as good models of the human visual system. However, there are currently many shortcomings of DCNNs, which preclude them as a model of human vision. For example, in the case of adversarial attacks, where adding small amounts of noise to an image, including an object, can lead to strong misclassification of that object. But for humans, the noise is often invisible. If vulnerability to adversarial noise cannot be fixed, DCNNs cannot be taken as serious models of human vision. Many studies have tried to add features of the human visual system to DCNNs to make them robust against adversarial attacks. However, it is not fully clear whether human vision inspired components increase robustness because performance evaluations of these novel components in DCNNs are often inconclusive. We propose a set of criteria for proper evaluation and analyze different models according to these criteria. We finally sketch future efforts to make DCCNs one step closer to the model of human vision.

READ FULL TEXT

page 3

page 18

research
01/02/2018

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Deep learning is at the heart of the current rise of machine learning an...
research
05/02/2019

Weight Map Layer for Noise and Adversarial Attack Robustness

Convolutional neural networks (CNNs) are known for their good performanc...
research
06/08/2023

Degraded Polygons Raise Fundamental Questions of Neural Network Perception

It is well-known that modern computer vision systems often exhibit behav...
research
06/15/2022

Human Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial Noises

Compared to human vision, computer vision based on convolutional neural ...
research
11/21/2021

Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attacks

Despite its great success, deep learning severely suffers from robustnes...
research
11/11/2020

Adversarial images for the primate brain

Deep artificial neural networks have been proposed as a model of primate...
research
08/06/2018

Adversarial Vision Challenge

The NIPS 2018 Adversarial Vision Challenge is a competition to facilitat...

Please sign up or login with your details

Forgot password? Click here to reset