Work

Robustness of Redundancy-Hardened Convolutional Neural Networks Against Adversarial Attacks

Year: 2024

Type: conference-paper

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.

Source: IEEE Pacific Rim International Symposium on Dependable Computing (PRDC)

DOI: 10.1109/prdc63035.2024.00034

Authors: Leonardo Alexandrino De Melo, Mauricio Gomes De Queiroz, Alberto Bosio, Rodrigo Possamai Bastos

Institutions: Lyon 1 Université, École Centrale de Lyon, Centre National de la Recherche Scientifique, Institut National des Sciences Appliquées de Lyon, Institut polytechnique de Grenoble, Techniques of Informatics and Microelectronics for Integrated Systems Architecture

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4403444892

FWCI: 0.294

Cites: 7

Cited by: 1

Related to: 10