SanitAIs: Unsupervised Data Augmentation to Sanitize Trojaned Neural Networks

09/09/2021
by   Kiran Karra, et al.
0

The application of self-supervised methods has resulted in broad improvements to neural network performance by leveraging large, untapped collections of unlabeled data to learn generalized underlying structure. In this work, we harness unsupervised data augmentation (UDA) to mitigate backdoor or Trojan attacks on deep neural networks. We show that UDA is more effective at removing the effects of a trigger than current state-of-the-art methods for both feature space and point triggers. These results demonstrate that UDA is both an effective and practical approach to mitigating the effects of backdoors on neural networks.

READ FULL TEXT

page 4

page 5

page 6

page 7

research
06/27/2022

Wav2Vec-Aug: Improved self-supervised training with limited data

Self-supervised learning (SSL) of speech representations has received mu...
research
11/02/2022

Joint Data and Feature Augmentation for Self-Supervised Representation Learning on Point Clouds

To deal with the exhausting annotations, self-supervised representation ...
research
04/29/2019

Unsupervised Data Augmentation

Despite its success, deep learning still needs large labeled datasets to...
research
06/20/2019

Efficient data augmentation using graph imputation neural networks

Recently, data augmentation in the semi-supervised regime, where unlabel...
research
10/11/2018

Perfusion parameter estimation using neural networks and data augmentation

Perfusion imaging plays a crucial role in acute stroke diagnosis and tre...
research
06/18/2018

HitNet: a neural network with capsules embedded in a Hit-or-Miss layer, extended with hybrid data augmentation and ghost capsules

Neural networks designed for the task of classification have become a co...
research
10/22/2020

Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Data

Unsupervised Data Augmentation (UDA) is a semi-supervised technique that...

Please sign up or login with your details

Forgot password? Click here to reset