Saved in:
Bibliographic Details
Main Authors: Acharya, Rabin Yu, Jeune, Laurens Le, Mentens, Nele, Ganji, Fatemeh, Forte, Domenic
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.04194
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911787598741504
author Acharya, Rabin Yu
Jeune, Laurens Le
Mentens, Nele
Ganji, Fatemeh
Forte, Domenic
author_facet Acharya, Rabin Yu
Jeune, Laurens Le
Mentens, Nele
Ganji, Fatemeh
Forte, Domenic
contents Deploying machine learning-based intrusion detection systems (IDSs) on hardware devices is challenging due to their limited computational resources, power consumption, and network connectivity. Hence, there is a significant need for robust, deep learning models specifically designed with such constraints in mind. In this paper, we present a design methodology that automatically trains and evolves quantized neural network (NN) models that are a thousand times smaller than state-of-the-art NNs but can efficiently analyze network data for intrusion at high accuracy. In this regard, the number of LUTs utilized by this network when deployed to an FPGA is between 2.3x and 8.5x smaller with performance comparable to prior work.
format Preprint
id arxiv_https___arxiv_org_abs_2311_04194
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Quantization-aware Neural Architectural Search for Intrusion Detection
Acharya, Rabin Yu
Jeune, Laurens Le
Mentens, Nele
Ganji, Fatemeh
Forte, Domenic
Cryptography and Security
Deploying machine learning-based intrusion detection systems (IDSs) on hardware devices is challenging due to their limited computational resources, power consumption, and network connectivity. Hence, there is a significant need for robust, deep learning models specifically designed with such constraints in mind. In this paper, we present a design methodology that automatically trains and evolves quantized neural network (NN) models that are a thousand times smaller than state-of-the-art NNs but can efficiently analyze network data for intrusion at high accuracy. In this regard, the number of LUTs utilized by this network when deployed to an FPGA is between 2.3x and 8.5x smaller with performance comparable to prior work.
title Quantization-aware Neural Architectural Search for Intrusion Detection
topic Cryptography and Security
url https://arxiv.org/abs/2311.04194