Conference proceeding
Error Correction Codes for Robust Classification with Neural Networks Under Sparse Noise
Conference record - Asilomar Conference on Signals, Systems, & Computers, pp.1333-1337
10/27/2024
DOI: 10.1109/IEEECONF60004.2024.10942763
Abstract
We consider the problem of designing neural network classifiers that are robust when their inputs are corrupted by sparse noise. We report on a series of experiments on the MNIST image dataset where we test the performance of neural network classifiers on images with a small number of corrupted pixels. We find that neural network classifiers are highly vulnerable to sparsely corrupted inputs, and this vulnerability remains even when substantial amounts of redundancy is added to the inputs. We show that this vulnerability can be effectively fixed by designing a real-numbered error correction code and using \ell_{1} minimization procedure to clean up the corrupted inputs.
Details
- Title: Subtitle
- Error Correction Codes for Robust Classification with Neural Networks Under Sparse Noise
- Creators
- Eva Riherd - University of Iowa,Department of Electrical and Computer Engineering,Iowa City,Iowa,USA,52240Raghu Mudumbai - University of Iowa,Department of Electrical and Computer Engineering,Iowa City,Iowa,USA,52240Weiyu Xu - University of Iowa,Department of Electrical and Computer Engineering,Iowa City,Iowa,USA,52240
- Resource Type
- Conference proceeding
- Publication Details
- Conference record - Asilomar Conference on Signals, Systems, & Computers, pp.1333-1337
- DOI
- 10.1109/IEEECONF60004.2024.10942763
- eISSN
- 2576-2303
- Publisher
- IEEE
- Language
- English
- Date published
- 10/27/2024
- Academic Unit
- Electrical and Computer Engineering
- Record Identifier
- 9984808540102771
Metrics
8 Record Views