Harnessing the Lemurs optimizer for adversarial attacks on deep neural networks
Abasi, Ammar Kamal Aloqaily, Moayad Guizani, Mohsen
Abasi, Ammar Kamal
Aloqaily, Moayad
Guizani, Mohsen
Supervisor
Department
Machine Learning
Embargo End Date
Type
Journal article
Date
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
The vulnerability of Deep Neural Networks (DNNs) to adversarial attacks reveals critical challenges in model robustness, particularly in sensitive applications. This paper introduces the Lemurs Optimizer for Adversarial Attacks (LO-Attack), a gradient-free metaheuristic algorithm inspired by swarm intelligence and lemur social behavior designed to generate adversarial examples. Unlike traditional gradient-based methods, LO-Attack operates effectively in white-box and black-box environments. Through evaluations on CIFAR-10, ImageNet, and MNIST, LO-Attack achieves a high fooling rate with minimal perturbation sizes, achieving competitive fooling rates compared to FGSM and DeepFool. Visualizations confirm that LO-Attack produces subtle perturbations that compromise model reliability without perceptible differences. The LO-Attack method offers a flexible and robust approach for adversarial attacks and has broader implications for NP-hard optimization challenges beyond neural network testing.
Citation
A.K. Abasi, M. Aloqaily, M. Guizani, "Harnessing the Lemurs optimizer for adversarial attacks on deep neural networks," Cluster Computing, vol. 29, no. 6, pp. 361-, 2026, https://doi.org/10.1007/s10586-026-06133-6.
Source
Cluster Computing
Conference
Keywords
Subjects
Source
Publisher
Springer Nature