WWIDECOM 2026
Conference Program

WIDECOM 2026

The 9th International Conference on Wireless, Intelligent and Distributed Environment for COMmunication

DatesOctober 28–30, 2026
VenueToronto Metropolitan University, Toronto, Canada
View scheduleMeet the speakers
3Days
2Keynotes
3Tutorials
5Sessions
21Papers

Invited speakers

Keynotes and Tutorials

Two keynote talks and three tutorials from leading researchers in cybersecurity, wireless communications and distributed intelligence.

Keynote Talk I

Prof. Wei Lu

Professor and Chair of Computer Science
Keene State College, University System of New Hampshire, USA

From Detection to Resilience: Securing AI-Enabled Healthcare Systems

Thursday, October 29 · 9:00 – 10:30 AM

Keynote Talk II

Dr. Sajal Saha

Assistant Professor of Computer Science
Brock University, Canada

From Prediction to Autonomy: The Evolving Role of AI in Network and Cyber Defense

Friday, October 30 · 9:00 – 10:20 AM

Tutorial I

Dr. Ahmed S. Khwaja

Senior Research Associate (WINCORE Lab) and Postdoctoral Fellow (DABNEL Lab)
Toronto Metropolitan University, Canada

Integrated Sensing and Communication for Imaging

Wednesday, October 28 · 10:00 – 11:30 AM

Tutorial II

Dr. Jagdeep Singh

Assistant Professor, Department of Computer Science and Engineering
Sant Longowal Institute of Engineering and Technology (SLIET), Longowal, India

Open-Source Intelligence (OSINT) for Modern Cybersecurity: Methodologies, Tools, and AI-Assisted Investigation

Thursday, October 29 · 2:00 – 3:30 PM

Tutorial III

Dr. Lilatul Ferdouse

Assistant Professor, Department of Physics and Computer Science
Wilfrid Laurier University, Waterloo, Canada

Federated Split Learning and Split Differential Privacy for Wireless Networks

Friday, October 30 · 2:30 – 3:50 PM

Program at a glance

Conference Schedule

All times are local (Toronto, Eastern Time). The program is subject to minor changes.

Wednesday, October 28, 2026

  1. Conference Inauguration and Welcome
  2. Tutorial I

    Integrated Sensing and Communication for Imaging

    Dr. Ahmed S. Khwaja, Toronto Metropolitan University, Canada

  3. Tea / Coffee Break

  4. Session I

    Session Chair: Dr. Jagdeep Singh, Sant Longowal Institute of Engineering and Technology (SLIET), Longowal, India
    1. 12:00 – 12:30 PMPaper 1: LLM-Based Compliance Auditing for Public Sector Infrastructure-as-CodeJohnson Nuviadenu, Themba Masombuka, Ernest Mnkandla and Malusi Sibiya
    2. 12:30 – 1:00 PMPaper 2: Mode Reverses Ranking: Live Evidence That Evaluation Format Determines Which LLM You Deploy for CybersecurityJustice Owusu Agyemang, Michael Agyare, Kwame Opuni-Boachie Obour Agyekum, Kwame Agyeman-Prempeh Agyekum, Francisca Adoma Acheampong and Jerry John Kponyo
    3. 1:00 – 1:30 PMPaper 3: Shadow Mode: A Risk-Free Validation Framework for AI-Driven Self-Healing in Government Digital InfrastructureJohnson Nuviadenu, Themba Masombuka, Ernest Mnkandla and Malusi Sibiya
  5. Lunch

  6. Session II

    Session Chair: Dr. Isaac Woungang, Toronto Metropolitan University, Toronto, Canada
    1. 2:30 – 3:00 PMPaper 4: AI-driven Dynamic Resource Allocation and Interference Management in Multi-BS ISAC Systems for 6G NetworksGeorge Prah II, Simon Amonovi, Ivy Safo-Mainoo, Dickson Fosu, Daniel Amaning, Justice Agyemang and James Gadze
    2. 3:00 – 3:30 PMPaper 5: O-DU-MoE-WPFM: Sparse Mixture-of-Experts Wireless Physical Layer Foundation Model for Real-Time PHY/MAC Inference at the O-RAN Open Distributed UnitDaniel Amaning, George Prah II, Simon Amonovi, Ivy Safo-Mainoo, Dickson Fosu, Justice Agyemang and James Gadze
    3. 3:30 – 4:00 PMPaper 6: Near-Field XL-RIS Channel Modelling: Non-Stationarity, Visibility Regions, and Beam-SquintIvy Georgina Sarfo-Mainoo, Dickson Fosu, Daniel Amaning, George Prah II, Simon Amonovi, Justice Agyemang and James Gadze
    4. 4:00 – 4:30 PMPaper 7: Emerging AI Paradigms for Privacy Preserving Edge Computing: Opportunities, Challenges and Future Research DirectionsAisha Aamir and Lilatul Ferdouse
    5. 4:30 – 5:00 PMPaper 8: Hardware-Quality-Aware AP Clustering for URLLC DVP in CF-mMIMODickson Marfo Fosu, Daniel Amaning, George Prah II, Simon Amonovi, Ivy Georgina Sarfo-Mainoo, Justice Owusu Agyemang and James Dzisi Gadze

Venue

Where to find us

Toronto Metropolitan University

350 Victoria Street

Toronto, ON M5B 2K3, Canada

October 28–30, 2026

Technical co-sponsors

Toronto Metropolitan University, Toronto, Canada

Springer, LNDECT Series

Keynote Talk I

Prof. Wei Lu

Professor and Chair of Computer Science
Keene State College, University System of New Hampshire, USA

Thursday, October 29 · 9:00 – 10:30 AM

Keynote title

From Detection to Resilience: Securing AI-Enabled Healthcare Systems

Abstract

AI-enabled healthcare systems increasingly rely on connected medical devices, wearable sensors, intelligent monitoring platforms, and distributed computing infrastructures. While these technologies create new opportunities for personalized and responsive care, they also introduce new cybersecurity, privacy, and reliability challenges. Protecting such systems requires more than detecting attacks after they occur; future healthcare platforms must be designed to understand threats, protect sensitive data, and remain resilient under adverse conditions.

This keynote presents a research journey from attack detection toward cyber resilience in AI-enabled healthcare systems. It highlights machine learning-based intrusion detection for the Internet of Medical Things, explainable analysis of cyberattacks, security vulnerabilities in connected medical devices, privacy-preserving and in-sensor computing, and AI-based intelligent health monitoring. Particular attention will be given to the limitations of conventional detection methods, the importance of explainability in security decision-making, and the need to move security and privacy protections closer to the sensing and hardware layers.

Drawing on recent research across IoMT networks, medical devices, edge intelligence, and healthcare AI, the talk will discuss how these areas can be integrated into a more comprehensive vision of cyber-resilient healthcare. The keynote will conclude with open challenges and future directions for building secure, explainable, privacy-aware, and resilient AI-enabled healthcare systems.

Biography

Wei Lu is Professor and Chair of Computer Science at Keene State College, part of the University System of New Hampshire. Before joining academia in the United States, he worked in the software industry and research sector, including positions at the German Research Center for Artificial Intelligence (DFKI), Q1 Labs (later acquired by IBM), and Bell Labs. He received his Ph.D. in Engineering and Computer Science from the University of Victoria, Canada; dual master’s degrees in Intellectual Property Law and Business Administration from the University of New Hampshire; and his M.S. and B.S. degrees in Electronics Engineering from Huazhong University of Science and Technology.

His research focuses on cybersecurity, artificial intelligence, biomedical informatics, and secure intelligent healthcare systems. With approximately 100 peer-reviewed journal articles, book chapters, and conference papers, his work has received more than 11,000 citations on Google Scholar. He currently serves as principal investigator on two active NIH-funded research projects totaling more than $1 million. A Senior Member of IEEE, Dr. Lu is the recipient of the 2021 KSC Faculty Distinction in Research and Scholarship Award and the author of two books published by Springer.
Keynote Talk II

Dr. Sajal Saha

Assistant Professor of Computer Science; Founder, INFORM Lab
Brock University, Canada

Friday, October 30 · 9:00 – 10:20 AM

Keynote title

From Prediction to Autonomy: The Evolving Role of AI in Network and Cyber Defense

Abstract

Networks are shifting from systems we monitor to systems that increasingly monitor, reason about, and defend themselves. This evolution is unfolding in stages: from predictive models that forecast traffic and flag anomalies, to federated and privacy-preserving learning, which lets distributed and resource-constrained devices detect threats collaboratively without exposing sensitive data, to explainable AI that turns model decisions into evidence a security analyst can trust and act on.

The next stage is already emerging: large language model (LLM) and retrieval-augmented generation (RAG) based agents that reason over telemetry and threat intelligence to support autonomous, real-time defense. In this presentation, we trace that journey and consider what it will take for these increasingly autonomous systems to be not just capable, but trustworthy enough to defend the network infrastructure we depend on.

Biography

Sajal Saha (Senior Member, IEEE) is an Assistant Professor of Computer Science at Brock University, Canada, and Founder of the INFORM Lab. He received the Ph.D. degree in Computer Science from Western University, Canada, where he was nominated for the Governor General’s Gold Medal, and the M.Sc. degree in Computer Science from Brock University, Canada, where he was recognized as a Distinguished Graduate. Before joining Brock, he held his first independent faculty appointment at the University of Northern British Columbia (UNBC), where he continues to hold an Adjunct Professor appointment and supervise graduate students.

His research focuses on Internet traffic analysis, cyber-attack detection and mitigation, privacy-preserving and federated learning, and quantum-secure AI systems. Dr. Saha has authored numerous peer-reviewed publications, and his work has been supported through national and institutional research grants. He also serves as a reviewer and technical program committee member for international journals and conferences.
Tutorial I

Dr. Ahmed S. Khwaja

Senior Research Associate (WINCORE Lab) and Postdoctoral Fellow (DABNEL Lab)
Toronto Metropolitan University, Canada

Wednesday, October 28 · 10:00 – 11:30 AM

Tutorial title

Integrated Sensing and Communication for Imaging

Abstract

Integrated sensing and communication (ISAC) is one of the core technologies for the upcoming 6G wireless networks. It enables merging of wireless communications and radar-like sensing onto a single platform, optimizing energy and spectrum usage. The sensing applications of ISAC include detecting the location, speed, and moving direction of objects, using the wireless signals reflected by the objects. A further application is the imaging of objects or an environment using ISAC-based radar imaging.

This tutorial presents an introduction to ISAC, radar imaging principles, and the use of ISAC for achieving radar imaging. The main aim of the tutorial is to enable attendees to gain a basic understanding of ISAC-based imaging concepts, allowing them to understand research literature in this field and extend these concepts in their research work.

Biography

Ahmed S. Khwaja received the Ph.D. degree in Signal Processing and Telecommunications from the University of Rennes 1, France. Currently, he is a Senior Research Associate with the Wireless Networking and Communication Research (WINCORE) Laboratory, Department of Electrical, Computer and Biomedical Engineering, and a Postdoctoral Fellow with the Distributed Applications and Broadband Network (DABNEL) Laboratory, Department of Computer Science, at Toronto Metropolitan University, Toronto, Canada.

His research interests include remote sensing, machine learning, and optimization problems in wireless communication systems and smart grid.
Tutorial II

Dr. Jagdeep Singh

Assistant Professor, Department of Computer Science and Engineering; Chief Information Security Officer
Sant Longowal Institute of Engineering and Technology (SLIET), Longowal, India

Thursday, October 29 · 2:00 – 3:30 PM

Tutorial title

Open-Source Intelligence (OSINT) for Modern Cybersecurity: Methodologies, Tools, and AI-Assisted Investigation

Abstract

Open-Source Intelligence (OSINT) has evolved from a largely manual investigative practice into a critical capability in modern cybersecurity. By systematically collecting, verifying, correlating, and analyzing publicly available information, OSINT supports actionable intelligence for attack-surface management, threat attribution, and incident response. However, its dual-use nature also enables adversary reconnaissance, highlighting the need for reliable investigative methodologies and responsible intelligence practices.

This tutorial provides a practical and methodological overview of the OSINT intelligence cycle, covering information collection, verification, analysis, and reporting. Participants will explore widely used tools across multiple investigative domains, including Maltego and SpiderFoot for link analysis and automation; Sherlock and Epieos for online identity investigations; Shodan, Censys, and Amass for internet-facing asset discovery; and Google Earth Pro, ADS-B Exchange, and MarineTraffic for geospatial analysis and movement tracking. Real-world case studies will demonstrate how these tools and techniques can be combined to support systematic investigations.

The tutorial further examines the emerging role of artificial intelligence (AI) in OSINT, focusing on how Large Language Models (LLMs) and Vision-Language Models (VLMs) can assist with entity extraction, visual geolocation, and knowledge-graph construction. It also explores agentic workflows for automating information gathering and cross-source correlation, while emphasizing the need for human validation of AI-generated findings. Key challenges, including data poisoning, hallucination-driven misattribution, and synthetic disinformation, will be discussed alongside legal, privacy, and evidentiary considerations. The tutorial concludes with practical recommendations for developing transparent, reproducible, and human-supervised AI-assisted OSINT workflows.

By bridging established investigative techniques with emerging AI capabilities, this tutorial aims to equip cybersecurity researchers and practitioners with the methodological understanding needed to conduct effective, reliable, and responsible OSINT investigations.

Keywords: Open source intelligence, cybersecurity, threat intelligence, large language models, agentic AI, attack-surface management, geospatial intelligence, digital forensics.

Biography

Dr. Jagdeep Singh is an Assistant Professor in the Department of Computer Science and Engineering at Sant Longowal Institute of Engineering and Technology (SLIET), Longowal, India (a Deemed-to-be University under the Ministry of Education, Government of India). He also serves as the institute’s Chief Information Security Officer (CISO), providing leadership in information security and cybersecurity initiatives. He holds a Ph.D. in Computer Engineering from the University of Delhi and is a Certified Information Security Manager (CISM) and Certified Ethical Hacker (CEH v13 AI). His research spans artificial intelligence, cybersecurity, federated learning, and anomaly detection in cyber-physical systems, with publications in venues associated with IEEE, Springer, and Elsevier and presentations at prominent international conferences, including IEEE ICC, IEEE GLOBECOM, IEEE CITS and IEEE INDICON.

Dr. Singh is Co-Principal Investigator of a CSR-supported project worth ₹40 lakh on AI-enabled cooperative multi-drone surveillance for road safety and landslide detection in Himachal Pradesh. He is a Senior Member of IEEE and of the Indian National Academy of Engineering (INAE), serves as an Editorial Board Member of Scientific Reports (Nature Portfolio), and is an AICTE-certified Master Trainer in High-Performance Computing and an AWS Academy Educator.

Dr. Singh led the winning team in both the Ideation and Prototype stages of the Indian Web Browser Development Challenge, organized by the Ministry of Electronics and Information Technology, Government of India. He was also selected as a Young Science and Technology Leader at ESTIC 2026, held at Bharat Mandapam, New Delhi.

He has chaired technical sessions at several international conferences, including ICAMS-2025 (NIT Hamirpur, in collaboration with IIT Roorkee), IEEE DICCT-2026, 2025 (Graphic Era Deemed University, Dehradun), and ICICST-2026 (Dr. B. R. Ambedkar NIT Jalandhar). His professional service includes reviewing manuscripts for leading journals such as IEEE Transactions on Information Forensics and Security, IEEE Internet of Things Journal, and IEEE Transactions on Dependable and Secure Computing. With more than 25 invited keynote and expert talks delivered at institutions across India, he actively contributes to advancing cybersecurity awareness, emerging technologies, and research-driven innovation.
Tutorial III

Dr. Lilatul Ferdouse

Assistant Professor, Department of Physics and Computer Science
Wilfrid Laurier University, Waterloo, Canada

Friday, October 30 · 2:30 – 3:50 PM

Tutorial title

Federated Split Learning and Split Differential Privacy for Wireless Networks

Abstract

Federated Learning (FL) is a distributed learning paradigm that performs Machine Learning (ML) training on the local datasets of multiple clients without requiring any training data points to be transmitted through the network. With an increased number of participating clients, FL’s performance thrives; however, it can also create difficulties due to the heterogeneous nature of the network. Two of the most challenging issues of FL are device and data heterogeneity, which refer to the differences among participating clients’ computational capacity and local data distribution, respectively. Due to device heterogeneity, clients with low computational capacity (low-CC) can potentially delay the FL process, while data heterogeneity can introduce bias in FL if a few clients in the network hold a dominating amount of training data points. Furthermore, the recent advancement of the gradient inversion concept has put the privacy characteristic of FL in question, since attackers can reconstruct a training data point with just the gradient values.

In this tutorial, we address three research problems of FL: (I) device heterogeneity, (II) data heterogeneity, and (III) security concerns. We will present the Federated Split Learning (FSL) framework and a Differential Privacy (DP) mechanism named Split-DP. FSL is an improved version of conventional FL, in which low-CC clients offload heavy computation to the edge server while performing the FL task, whereas Split-DP addresses the threat of gradient inversion attacks in FL. This tutorial will discuss the design principles, theoretical foundations, and practical implementation of these frameworks, supported by experimental results in resource-constrained environments, including Industrial IoT and UAV networks.

Biography

Dr. Lilatul Ferdouse is an Assistant Professor in the Department of Physics and Computer Science at Wilfrid Laurier University, Waterloo, Canada, specializing in applied machine learning for smart city applications, computer networks, and wireless communication. She has made substantial contributions to research, academic service, and professional engagement, particularly within the IEEE community.

Her research focuses on advanced topics such as Industrial IoT, 5G/B5G, Cloud-RAN, edge computing, and AI-driven resource optimization, with numerous high-impact publications in top-tier IEEE and Springer journals and international conferences. She has secured competitive research funding, including a Startup Research Fund and a five-year NSERC Discovery Grant, and has supervised multiple graduate and undergraduate students at Wilfrid Laurier University, guiding research in digital twin systems, federated learning, and smart city applications.