AI Optimisers and Malware Detection Using Imagary on the Rasberry Pi

Phil Steadman; Rajkumar Singh Rathore; Chaminda Hewage; Paul Jenkins

doi:10.1109/iscon65210.2025.11341451

AI Optimisers and Malware Detection Using Imagary on the Rasberry Pi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Given the diverse and long-lasting nature of Internet of Things (IoT) hardware, which often results in significant disparities in operating systems, processing power, and RAM, this study evaluates the performance of various AI optimisers for image-based malware detection on Raspberry Pi 4 and 5. The paper discusses the new Raspberry Pi AI HAT and explains the rationale for selecting a lightweight model. Due to the inability of Raspberry Pi devices to handle the training process, which frequently led to crashes, model training was performed on a MacBook M2. However, the Raspberry Pi units were capable of processing batches of 32 images to compare prediction outputs and success rates. This work also details the challenges encountered with different hardware and software variants. Significant findings include the achievement of 100’%’ prediction accuracy with certain optimisers, and the paper presents a comparative analysis of these optimisers' performance.

Original language	English
Title of host publication	2025 7th International Conference on Information Systems and Computer Networks (ISCON)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1-8
Number of pages	8
ISBN (Electronic)	9798331597443
ISBN (Print)	9798331597450
DOIs	https://doi.org/10.1109/iscon65210.2025.11341451
Publication status	Published - 5 Sept 2025
Event	2025 7th International Conference on Information Systems and Computer Networks (ISCON) - Mathura, India Duration: 5 Sept 2025 → 6 Sept 2025

Conference

Conference	2025 7th International Conference on Information Systems and Computer Networks (ISCON)
Country/Territory	India
City	Mathura
Period	5/09/25 → 6/09/25

Keywords

Artificial Intelligence
Convolutional neural networks. Image processing
I1oT
Malware
Raspberry Pi

Access to Document

10.1109/iscon65210.2025.11341451

Cite this

@inproceedings{3da9d001245845ad8ba68dae52855ed1,

title = "AI Optimisers and Malware Detection Using Imagary on the Rasberry Pi",

abstract = "Given the diverse and long-lasting nature of Internet of Things (IoT) hardware, which often results in significant disparities in operating systems, processing power, and RAM, this study evaluates the performance of various AI optimisers for image-based malware detection on Raspberry Pi 4 and 5. The paper discusses the new Raspberry Pi AI HAT and explains the rationale for selecting a lightweight model. Due to the inability of Raspberry Pi devices to handle the training process, which frequently led to crashes, model training was performed on a MacBook M2. However, the Raspberry Pi units were capable of processing batches of 32 images to compare prediction outputs and success rates. This work also details the challenges encountered with different hardware and software variants. Significant findings include the achievement of 100{\textquoteright}\%{\textquoteright} prediction accuracy with certain optimisers, and the paper presents a comparative analysis of these optimisers' performance.",

keywords = "Artificial Intelligence, Convolutional neural networks. Image processing, I1oT, Malware, Raspberry Pi",

author = "Phil Steadman and Rathore, \{Rajkumar Singh\} and Chaminda Hewage and Paul Jenkins",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 7th International Conference on Information Systems and Computer Networks (ISCON) ; Conference date: 05-09-2025 Through 06-09-2025",

year = "2025",

month = sep,

day = "5",

doi = "10.1109/iscon65210.2025.11341451",

language = "English",

isbn = "9798331597450",

pages = "1--8",

booktitle = "2025 7th International Conference on Information Systems and Computer Networks (ISCON)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

Steadman, P , Rathore, RS , Hewage, C & Jenkins, P 2025, AI Optimisers and Malware Detection Using Imagary on the Rasberry Pi. in 2025 7th International Conference on Information Systems and Computer Networks (ISCON). Institute of Electrical and Electronics Engineers (IEEE), pp. 1-8, 2025 7th International Conference on Information Systems and Computer Networks (ISCON), Mathura, India, 5/09/25. https://doi.org/10.1109/iscon65210.2025.11341451

AI Optimisers and Malware Detection Using Imagary on the Rasberry Pi. / Steadman, Phil ; Rathore, Rajkumar Singh ; Hewage, Chaminda et al.
2025 7th International Conference on Information Systems and Computer Networks (ISCON). Institute of Electrical and Electronics Engineers (IEEE), 2025. p. 1-8.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - AI Optimisers and Malware Detection Using Imagary on the Rasberry Pi

AU - Steadman, Phil

AU - Rathore, Rajkumar Singh

AU - Hewage, Chaminda

AU - Jenkins, Paul

PY - 2025/9/5

Y1 - 2025/9/5

N2 - Given the diverse and long-lasting nature of Internet of Things (IoT) hardware, which often results in significant disparities in operating systems, processing power, and RAM, this study evaluates the performance of various AI optimisers for image-based malware detection on Raspberry Pi 4 and 5. The paper discusses the new Raspberry Pi AI HAT and explains the rationale for selecting a lightweight model. Due to the inability of Raspberry Pi devices to handle the training process, which frequently led to crashes, model training was performed on a MacBook M2. However, the Raspberry Pi units were capable of processing batches of 32 images to compare prediction outputs and success rates. This work also details the challenges encountered with different hardware and software variants. Significant findings include the achievement of 100’%’ prediction accuracy with certain optimisers, and the paper presents a comparative analysis of these optimisers' performance.

AB - Given the diverse and long-lasting nature of Internet of Things (IoT) hardware, which often results in significant disparities in operating systems, processing power, and RAM, this study evaluates the performance of various AI optimisers for image-based malware detection on Raspberry Pi 4 and 5. The paper discusses the new Raspberry Pi AI HAT and explains the rationale for selecting a lightweight model. Due to the inability of Raspberry Pi devices to handle the training process, which frequently led to crashes, model training was performed on a MacBook M2. However, the Raspberry Pi units were capable of processing batches of 32 images to compare prediction outputs and success rates. This work also details the challenges encountered with different hardware and software variants. Significant findings include the achievement of 100’%’ prediction accuracy with certain optimisers, and the paper presents a comparative analysis of these optimisers' performance.

KW - Artificial Intelligence

KW - Convolutional neural networks. Image processing

KW - I1oT

KW - Malware

KW - Raspberry Pi

UR - https://www.scopus.com/pages/publications/105033366556

U2 - 10.1109/iscon65210.2025.11341451

DO - 10.1109/iscon65210.2025.11341451

M3 - Conference contribution

SN - 9798331597450

SP - 1

EP - 8

BT - 2025 7th International Conference on Information Systems and Computer Networks (ISCON)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2025 7th International Conference on Information Systems and Computer Networks (ISCON)

Y2 - 5 September 2025 through 6 September 2025

ER -

AI Optimisers and Malware Detection Using Imagary on the Rasberry Pi

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this