Robustness of Redundancy-Hardened Convolutional Neural Networks Against Adversarial Attacks

Convolutional Neural Networks (CNNs) are vulnerable to undetectable manipulated inputs that reduce model accuracy. There are several methods to counter these Adversarial Attacks, however, resource-constrained systems require simpler solutions due to memory and processing limitations. This work explores the application of single-layer redundancy to implement a dynamic model in TensorFlow CNNs and its impact on mitigating Adversarial Attacks.

Authors

Institutions

Publication Details

Published
2024-11-13
DOI
https://doi.org/10.1109/prdc63035.2024.00034
Primary Topic
Adversarial Robustness in Machine Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Robustness of Redundancy-Hardened Convolutional Neural Networks Against Adversarial Attacks

Rodrigo Possamai Bastos, Maurício Gomes de Queiroz, Alberto Bosio, Leonardo Alexandrino de Melo
Adversarial Robustness in Machine Learning
article

Robustness of Redundancy-Hardened Convolutional Neural Networks Against Adversarial Attacks

Rodrigo Possamai Bastos, Maurício Gomes de Queiroz, Alberto Bosio, Leonardo Alexandrino de Melo
article en

Abstract

Convolutional Neural Networks (CNNs) are vulnerable to undetectable manipulated inputs that reduce model accuracy. There are several methods to counter these Adversarial Attacks, however, resource-constrained systems require simpler solutions due to memory and processing limitations. This work explores the application of single-layer redundancy to implement a dynamic model in TensorFlow CNNs and its impact on mitigating Adversarial Attacks.

Université Claude Bernard Lyon 1 (FR), Institut polytechnique de Grenoble (FR), École Centrale de Lyon (FR), Centre National de la Recherche Scientifique (FR), Institut National des Sciences Appliquées de Lyon (FR), École d'Ingénieurs en Chimie et Sciences du Numérique (FR), Université Grenoble Alpes (FR)
Openalex Percentile: Top 84%
Adversarial Robustness in Machine Learning
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Robustness of Redundancy-Hardened Convolutional Neural Networks Against Adversarial Attacks — Rodrigo Possamai Bastos, Maurício Gomes de Queiroz, et al. · (2024) | TGRS Research Map | TGRS