Research Visit

Currently a visiting PhD researcher at ETH Zürich, Integrated Systems Laboratory (D-ITET), Mar.–Jun. 2026. Expected thesis defense in mid-2026.

Get in Touch

About Me

I am a Ph.D. candidate at the University of Oulu, working under the supervision of Dr. Panos Kostakos and Dr. Lauri Lovén. My research focuses on the intersection of cybersecurity and artificial intelligence, with specific expertise in Federated Learning, Intrusion Detection Systems, Generative AI, LLM-powered security automation, and Threat Intelligence.

I have 5+ years of hands-on experience building and deploying production-grade AI and Generative AI systems, including LLM APIs, RAG pipelines, and multi-agent architectures applied to complex, real-world security domains. My work contributes to securing critical infrastructure and modern networks (5G/6G) by developing decentralized, privacy-preserving security mechanisms.

Since March 2026, I am conducting a funded research visit at ETH Zürich, Integrated Systems Laboratory (D-ITET), focusing on efficient and secure AI systems.

Federated Learning Intrusion Detection Generative AI & LLMs Explainable AI 5G/6G Security Privacy-Preserving ML Multi-Agent Architectures RAG Pipelines

Education

Dec 2021 – Present

Doctor of Science (Tech) in Computer Science & Engineering

University of Oulu, Finland

Focus: Cybersecurity, Federated Learning, GenAI, and Intrusion Detection Systems. Expected completion: mid-2026.

2014 – Feb 2017

Master of Science in Software Engineering

2010 – 2014

Bachelor of Science in Software Engineering

Publications

30+ peer-reviewed
2026

Chain of Simulation: A Dual-Mode Reasoning Framework for Large Language Models with Dynamic Problem Routing

S. Sheikhi

arXiv:2602.02842 · Preprint

Hybrid Reputation Aggregation: A Robust Defense Mechanism for Adversarial Federated Learning in 5G and Edge Network Environments

S. Sheikhi, P. Kostakos, L. Lovén

IEEE Open J. Commun. Soc., vol. 7, pp. 370–385
2025

Cognitive SOC: Evidence-Backed Narrative Generation for Security Operations with Multi-Agent LLM Architecture

S. Sheikhi, P. Kostakos, L. Lovén

IEEE BigData 2025, pp. 7027–7036

SLMFORGE: Small Language Models for Federated Feature Selection via Union Aggregation in Cybersecurity

S. Sheikhi

IEEE BigData 2025, pp. 4784–4792

FedDTKG: Federated Temporal Graph Learning with Adaptive Loss for Robust 5G Attack Detection under Extreme Class Imbalance

S. Sheikhi, L. Lovén, S. Pirttikangas, P. Kostakos

MSWiM 2025, Barcelona, pp. 803–806

Federated Variational Autoencoders for Unsupervised Anomaly Detection in Distributed 5G Networks

S. Sheikhi, A. Ghaffari, A. Amiri, L. Lovén

SoftCOM 2025, Split, pp. 1–6

A Feature-Aware Federated Learning Framework for Unsupervised Anomaly Detection in 5G Networks

S. Sheikhi, L. Lovén, P. Kostakos

IEEE CSCN 2025, Bologna, pp. 1–7

Optimized Contrastive Transformer Models for Self-Supervised 5G Network Intrusion Detection

S. Sheikhi, P. Kostakos, S. Pirttikangas, L. Lovén

GACLM 2025, Valencia, pp. 142–150

Bridging Theory and Practice: Addressing Current Cybersecurity Gaps in Industry 5.0

S. Sheikhi, M. Eceiza, C. Arellano, O. López, S. Kelnberger, R. Lindner, J. Partanen, L. Lovén

IEEE Access, 2025

Large Language Models in the 6G-Enabled Computing Continuum: a White Paper

M. Abel, I. Ahmad, C. Alvarez Casado, …, S. Sheikhi, et al.

University of Oulu, 2025
Under Review / Submitted

ChainAdversary: A Retrieval-Augmented LLM Framework for Generating Realistic Attack Scenarios and Incident Response Playbooks

S. Sheikhi, P. Kostakos, L. Lovén

Under Review

Enhancing Security of Connected Medical Devices in 5G Networks using an Unsupervised Federated Learning Model

S. Sheikhi, P. Kostakos

Submitted
2024

Effective Anomaly Detection in 5G Networks via Transformer-Based Models and Contrastive Learning

S. Sheikhi, P. Kostakos, S. Pirttikangas

CSNet 2024, pp. 38–43

Advancing Security in 5G Core Networks Through Federated Time Series Modeling

S. Sheikhi, P. Kostakos

IEEE CSR 2024, pp. 353–356

Safeguarding Cyberspace: Enhancing Malicious Website Detection with PSO-Optimized XGBoost and Firefly-Based Feature Selection

S. Sheikhi, P. Kostakos

Computers & Security, 142:103885

White Paper: Ensuring a Secure Future — Comprehensive Insights into 6G IoT Security and Privacy

IDUNN Project, 2024

White Paper
2023

Cyber Threat Hunting Using Unsupervised Federated Learning and Adversary Emulation

S. Sheikhi, P. Kostakos

IEEE CSR 2023

DDoS Attack Detection Using Unsupervised Federated Learning for 5G Networks and Beyond

S. Sheikhi, P. Kostakos

EuCNC & 6G Summit 2023

Edge Intelligence (Book Chapter)

S. Sheikhi

In: Security and Privacy Vision in 6G, Wiley, 2023

Autonomous Federated Learning for Distributed Intrusion Detection Systems in Public Networks

A. Mahmoodi, S. Sheikhi, E. Peltonen, P. Kostakos

IEEE Access, 11, 121325–121339
2022

A Novel Anomaly-Based Intrusion Detection Model Using PSOGWO-Optimized BP Neural Network and GA-Based Feature Selection

S. Sheikhi, P. Kostakos

Sensors, 22(23):9318

An Efficient Rotation Forest-Based Ensemble Approach for Predicting Severity of Parkinson's Disease

S. Sheikhi, M. T. Kheirabadi

J. Healthcare Engineering, 2022
2021 & Earlier

An Effective Fake News Detection Method Using WOA-xgbTree Algorithm and Content-Based Features

S. Sheikhi

Applied Soft Computing, 109, 107559, 2021

A Novel Scheme for Improving Accuracy of KNN Classification Algorithm Based on the New Weighting Technique and Stepwise Feature Selection

S. Sheikhi, M. T. Kheirabadi, A. Bazzazi

J. Information Technology Management, 12(4):90–104, 2020

An Efficient Method for Detection of Fake Accounts on the Instagram Platform

S. Sheikhi

Revue d'Intelligence Artificielle, 34(4):429–436, 2020

An Effective Model for SMS Spam Detection Using Content-Based Features and Averaged Neural Network

S. Sheikhi, M. T. Kheirabadi, A. Bazzazi

Int. J. Engineering, 33(2):221–228, 2020

Forecasting Shear Stress Parameters in Rectangular Channels Using New Soft Computing Methods

Z. Sheikh Khozani, S. Sheikhi, W. H. M. Wan Mohtar, A. Mosavi

PLOS One, 15(4):e0229731, 2020

Method for Replica Selection in the Internet of Things Using a Hybrid Optimisation Algorithm

K. Wakil, S. Panahi, H. Nazif, K. Abnoosian, S. Sheikhi

IET Communications, 13(17):2820–2826, 2019

Research Projects

H2020 IDUNN: A Cognitive Detection System for Cybersecure Operational Technologies

EU H2020
Role: Researcher & Developer PI: Dr. Susanna Pirttikangas Period: 2021–2024

End-to-end GenAI security platform integrating OpenAI GPT models and RAG pipelines for interpretable, evidence-backed threat intelligence. Cloud-native, microservices-based anomaly detection system with Explainable AI (SHAP, LIME) deployed on Kubernetes in production. Full MLOps stack (MLflow, Kubeflow, Seldon Core). Demonstrated live to Portuguese National Cybersecurity Center, Portuguese Military Academy, and Bittium.

LLM APIs (GPT) RAG Pipelines Federated Learning MLflow Kubernetes Kubeflow Seldon Core SHAP/LIME

H2020 NESTOR: An Enhanced Pre-Frontier Intelligence Picture to Safeguard European Borders

EU H2020
Role: Developer PI: Dr. Panos Kostakos Period: 2021–2023

Developed an augmented reality mapping application for HoloLens 2, integrating Kafka technology for seamless communication platform integration. Conducted final pilot demonstrations and trained EU national authorities in AR applications for border management.

Apache Kafka HoloLens 2 AR/MR

Professional Experience

Mar 2026 – Jun 2026

Visiting PhD Researcher

ETH Zürich, Integrated Systems Laboratory (D-ITET), Switzerland
  • Funded research visit on efficient and secure AI systems
  • Supported by 6GESS & DigiHealth Visitor Program research mobility grant (EUR 7,000)
Dec 2021 – Present

Doctoral Researcher

University of Oulu, Finland
  • Designed and delivered production-grade AI-powered applications within EU H2020 projects (IDUNN, NESTOR)
  • Built and deployed LLM-powered automation tools integrating OpenAI GPT, RAG pipelines, and multi-agent architectures
  • Architected scalable cloud-native platforms (Kubernetes, Docker, Kafka, microservices)
  • Coordinated development across international partner organizations in EU H2020 consortia
  • Mentored 5 Master's and 6 Bachelor's students (2022–2025)
  • Published 15+ peer-reviewed papers including IEEE BigData 2025
2014 – 2018

Senior Software Engineer & Web Developer

Hadid Entezar Industrial Company, Tehran, Iran
  • Designed and developed web applications and internal tools, including CRM systems
  • Built desktop and mobile applications tailored to business requirements
  • Collaborated directly with stakeholders to define requirements and iterate on usability

Grants & Awards

6GESS & DigiHealth Visitor Program — Research Mobility Grant

University of Oulu · 2026 · Funded research visit to ETH Zürich, Integrated Systems Laboratory, on efficient and secure AI systems

EUR 7,000

Tauno Tönningin Säätiö — Research Grant

2025 · Towards Collaborative Defense Mechanisms for Edge-Cloud Architectures

EUR 4,000

Technical Skills

AI & LLM

LLM APIs (OpenAI GPT) RAG Pipelines Multi-Agent Architectures Prompt Engineering LangChain Hugging Face Transformers

ML/AI & Cybersecurity

Federated Learning Intrusion Detection TensorFlow PyTorch Scikit-learn SHAP/LIME Threat Hunting Anomaly Detection

Cloud & Platform Infrastructure

Kubernetes Docker Kafka MLflow Kubeflow Seldon Core REST APIs Microservices

Programming & Tools

Python Java C++ SQL MATLAB R Git LaTeX

Teaching Experience

Guest Lecturer, Distributed Systems (521290S)

University of Oulu · Feb 2026 · Lectures on Fault Tolerance and Security in Distributed Systems

Teaching Assistant, Internet of Things (IoT)

University of Oulu · Fall 2025

Teaching Assistant, Internet of Things (IoT)

University of Oulu · Fall 2024

Teaching Assistant, Applied Computer Projects 1 & 2

University of Oulu · Spring 2024

Teaching Assistant, Cybersecurity I: Ethical Hacking

University of Oulu · Fall 2023

Teaching Assistant, Applied Computer Projects 1 & 2

University of Oulu · Spring & Autumn 2022