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

11/21/2021
by   Kaiyuan Liu, et al.
0

Despite its great success, deep learning severely suffers from robustness; that is, deep neural networks are very vulnerable to adversarial attacks, even the simplest ones. Inspired by recent advances in brain science, we propose the Denoised Internal Models (DIM), a novel generative autoencoder-based model to tackle this challenge. Simulating the pipeline in the human brain for visual signal processing, DIM adopts a two-stage approach. In the first stage, DIM uses a denoiser to reduce the noise and the dimensions of inputs, reflecting the information pre-processing in the thalamus. Inspired from the sparse coding of memory-related traces in the primary visual cortex, the second stage produces a set of internal models, one for each category. We evaluate DIM over 42 adversarial attacks, showing that DIM effectively defenses against all the attacks and outperforms the SOTA on the overall robustness.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/29/2022

Mel Frequency Spectral Domain Defenses against Adversarial Attacks on Speech Recognition Systems

A variety of recent works have looked into defenses for deep neural netw...
research
04/09/2018

A theory of consciousness: computation, algorithm, and neurobiological realization

The most enigmatic aspect of consciousness is the fact that it is felt, ...
research
03/27/2017

Biologically inspired protection of deep networks from adversarial attacks

Inspired by biophysical principles underlying nonlinear dendritic comput...
research
03/16/2021

Bio-inspired Robustness: A Review

Deep convolutional neural networks (DCNNs) have revolutionized computer ...
research
02/13/2020

Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks

Convolutional neural networks are vulnerable to small ℓ^p adversarial at...
research
07/16/2023

On the Robustness of Split Learning against Adversarial Attacks

Split learning enables collaborative deep learning model training while ...
research
06/20/2023

Towards a robust and reliable deep learning approach for detection of compact binary mergers in gravitational wave data

The ability of deep learning (DL) approaches to learn generalised signal...

Please sign up or login with your details

Forgot password? Click here to reset