Bio Summary:

Hamid Bostani is a Ph.D. candidate in the Digital Security group at Radboud University in Nijmegen, The Netherlands. His expertise lies in Adversarial Machine Learning, Machine Learning, Deep Learning, Malware Detection, Intrusion Detection Systems, and Internet of Things. With a Master’s in Computer Engineering from Islamic Azad University in Tehran, Iran, he has been recognized for his outstanding contributions in research and academia.

Education:

Ph.D. Candidate, Digital Security group, Radboud University, Nijmegen, The Netherlands (2020-Present)

M.Sc. in Computer Engineering, Islamic Azad University, Tehran, Iran (2012-2015)

B.Sc. in Computer Engineering, Islamic Azad University, Shiraz, Iran (2004-2008)

Research Focus:

Hamid’s Ph.D. research is centered on improving the Adversarial Robustness of Machine Learning-based Malware Detection against Real-World Threat Models. His supervisors are Dr. Veelasha Moonsamy and Prof. Erik Poll.

Professional Journey:

Visiting Scholar at Cybersecurity Group, King’s College University, London (Oct. 2023–Present)

Visiting Scholar at Systems Security Lab, University College London (Oct. 2023–Present)

Project Manager in Developing Integrated Cloud Infrastructure for NOET (Jan. 2020–Sept. 2020)

Senior Researcher in Developing a New Generation of Optimum-path Forest (OPF) (Mar. 2017–Nov. 2019)

Senior Developer in Developing Event-based WSN Simulator Based on RPL (Apr.–Jun. 2015)

Honors & Awards:

Fully-Funded Fellowship (Radboud University, Oct. 2020)

Best Employee Award (NOET, Nov. 2019)

Best Thesis Award (IAU, May 2017)

Outstanding Researcher Award (IAU, Dec. 2017)

Outstanding Paper Award (ICSPIS’2016)

Publications Top Noted & Contributions:

9 Journals, including Computers & Security, Information Sciences, and Pattern Recognition

3 Conferences, including IEEE Symposium on Security and Privacy (IEEE S&P 2024)

Title: Hybrid of Anomaly-Based and Specification-Based IDS for Internet of Things using Unsupervised OPF Based on MapReduce Approach

• Authors: H. Bostani, M. Sheikhan
• Published in: Computer Communications, 2017
• Summary: This paper presents a hybrid intrusion detection system for IoT. It combines anomaly-based and specification-based approaches using unsupervised Optimum-Path Forest (OPF) based on a MapReduce approach. The aim is to enhance the security of IoT environments.

Title: Hybrid of Binary Gravitational Search Algorithm and Mutual Information for Feature Selection in Intrusion Detection Systems

• Authors: H. Bostani, M. Sheikhan
• Published in: Soft Computing, 2015
• Summary: This paper introduces a hybrid approach utilizing a binary gravitational search algorithm and mutual information for feature selection in intrusion detection systems. The focus is on enhancing the efficiency and effectiveness of feature selection in the context of security.

Title: Modification of Supervised OPF-Based Intrusion Detection Systems using Unsupervised Learning and Social Network Concept

• Authors: H. Bostani, M. Sheikhan
• Published in: Pattern Recognition, 2017
• Summary: The paper discusses modifications to supervised Optimum-Path Forest (OPF)-based intrusion detection systems using unsupervised learning and social network concepts. The goal is to improve the performance of intrusion detection systems through these modifications.

Title: A Hybrid Intrusion Detection Architecture for Internet of Things

• Authors: M. Sheikhan, H. Bostani
• Published in: 2016 8th International Symposium on Telecommunications (IST)
• Summary: This paper presents a hybrid intrusion detection architecture specifically designed for the Internet of Things (IoT). The architecture aims to enhance the security of IoT devices and networks.

Title: A Security Mechanism for Detecting Intrusions in Internet of Things Using Selected Features Based on MI-BGSA

• Authors: M. Sheikhan, H. Bostani
• Published in: International Journal of Information & Communication Technology Research
• Summary: The paper introduces a security mechanism for detecting intrusions in IoT using selected features based on the MI-BGSA (Mutual Information – Binary Gravitational Search Algorithm) approach.

Author Metrics:

Google Scholar (January 2024)

• Citations: 517
• h-index: 6

Research Timeline:

Ph.D. Candidate (Oct. 2020-Present)

Master’s in Computer Engineering (2012-2015)

Bachelor’s in Computer Engineering (2004-2008)