Ali A. Ghorbani

Ali A. Ghorbani

Auto-generated profile, based on publicly available information

Ali A. Ghorbani

University of New Brunswick (UNB),Fredericton,Canada

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2021
Verified
Conference Paper
Closed access
MEMasoud Erfani
Masoud Erfani
FSFarzaneh Shoeleh
Farzaneh Shoeleh
Sajjad DadkhahSajjad Dadkhah
Sajjad Dadkhah
BKBarjinder Kaur
Barjinder Kaur
PXPulei Xiong
Pulei Xiong
AGAli A. Ghorbani
Ali A. Ghorbani
Internet of Things (IoT) devices' unique identity and adequate network infrastructure of physical objects em-bedded with software, actuators, and sensors create an open playground for various cybersecurity attacks. Recently, several researchers attempted to simulate diverse datasets to mimic the behavior of IoT devices and potential attacks in this field. However, since more new and dangerous attacks are being produced, a more diverse and universal dataset is required in this field. This paper proposes a framework to enrich the IoT datasets in two directions: Vertical and Horizontal. The Vertical aspect merges famous state-of-the-art IoT datasets, and in the Horizontal aspect, we propose a unique and new set of features to present the behavior of IoT devices in more diverse settings. Our experimental results demonstrate that the new simulated datasets enhanced by our method have achieved better performance in classifying cybersecurity attacks with various machine learning algorithms. All the generated datasets and codes created for this paper are publicly available in https://www.unb.ca/cic/datasets/enricheddataset.html.

20 May 2022 in Iranian Journal of Science and Technology, Transactions of Electrical Engineering
Verified
Journal Article
Closed access
PDF file
AGAli Ghorbani
Ali Ghorbani
SFSeyed Mostafa Fakhrahmad
Seyed Mostafa Fakhrahmad

9 November 2022
Verified
Conference Paper
Closed access
MAMahdi Abrishami
Mahdi Abrishami
Sajjad DadkhahSajjad Dadkhah
Sajjad Dadkhah
ENEuclides Carlos Pinto Neto
Euclides Carlos Pinto Neto
PXPulei Xiong
Pulei Xiong
SIShahrear Iqbal
Shahrear Iqbal
AGAli A. Ghorbani
Ali A. Ghorbani
With the increased usage of Internet of Things (IoT) devices in recent years, various Machine Learning (ML) algorithms have also developed dramatically for attack detection in this domain. However, the ML models are exposed to different classes of adversarial attacks that aim to fool a model into making an incorrect prediction. For instance, label manipulation or label flipping is an adversarial attack where the adversary attempts to manipulate the label of training data that causes the trained model biased and/or with decreased performance. However, the number of samples to be flipped in this category of attack can be restricted, giving the attacker a limited target selection. Due to the great significance of securing ML models against Adversarial Machine Learning (AML) attacks particularly in the IoT domain, this research presents an extensive review of AML in IoT. Then, a classification of AML attacks is presented based on the literature which sheds light on the future research in this domain. Next, this paper investigates the negative impact levels of applying the malicious label-flipping attacks on IoT data. We devise label-flipping scenarios for training a Support Vector Machine (SVM) model. The experiments demonstrate that the label flipping attacks impact the performance of ML models. These results can lead to designing more effective and powerful attack and defense mechanisms in adversarial settings. Finally, we show the weaknesses of the K-NN defense method against the random label flipping attack.