Aymen Bouferroum

Channel State Information (CSI) is a widely used Wi-Fi sensing modality, and models are commonly trained on data simulated by adding noise (most often additive white Gaussian noise) to recorded channel estimates. Testing this assumption on six commodity receivers across two indoor environments, we show it does not hold: automatic gain control compresses the channel estimate multiplicatively, producing amplitude distributions that no additive noise variance can reproduce. We propose MQTC, a measurement-calibrated model combining per-subcarrier quantile mapping, temporal filtering, and copula-based cross-subcarrier reordering, which reduces amplitude error 8-fold and closes 89% of the aggregate fidelity gap. Classifiers trained on MQTC-simulated data recover 93% of real-data jamming-detection performance, while AWGN-trained classifiers remain near random.

@misc{bouferroum2026csisimulationadditivenoise,
      title={CSI Simulation: Why Additive Noise Fails and How to Fix It},
      author={Aymen Bouferroum and Ildi Alla and Vincent Lenders and Valeria Loscri},
      year={2026},
      eprint={2607.01882},
      archivePrefix={arXiv},
      primaryClass={cs.NI},
      url={https://arxiv.org/abs/2607.01882},
}

Radio-frequency jamming poses a critical threat to the availability of wireless Industrial IoT networks. CITADEL is a lightweight, two-stage hierarchical pipeline that uses only Channel State Information (CSI), natively available on commodity IIoT devices, to detect and classify jamming attacks including previously unseen ones. Across 6 known attack types and 15 zero-day scenarios it achieves 100% known-attack detection and 97.1% zero-day detection at a 0.4% false-positive rate, resists white-box and black-box adversarial evasion, and completes end-to-end inference in 14.2 ms at 95.9 mJ on an edge GPU, outperforming eight baselines across detection, generalization, and robustness.

@misc{bouferroum2026citadelcsibasedjammingdetection,
      title={CITADEL: CSI-Based Jamming Detection and Open-Set Classification for IIoT Networks},
      author={Aymen Bouferroum and Ildi Alla and Valeria Loscri and Abderrahim Benslimane and Vincent Lenders},
      year={2026},
      eprint={2606.22939},
      archivePrefix={arXiv},
      primaryClass={cs.CR},
      url={https://arxiv.org/abs/2606.22939},
}

The Industrial IoT introduces serious security challenges as resource-constrained devices join critical processes, yet most defenses address a single layer and remain confined to simulation. This paper presents the research framework of my doctoral thesis: a lightweight, ML-based, multi-layer security framework for IIoT. Building on the Tm-IIoT trust model and the Hybrid IIoT (H-IIoT) architecture, it introduces the Trust Convergence Acceleration (TCA) approach, up to 28.6% faster trust convergence under degraded networks while staying robust to adversarial behavior, and proposes a real-world deployment on affordable, open-source hardware, extending toward multi-layer and physical-layer threat detection with resilience to adversarial ML.

@article{bouferroum2026toward,
  title={Toward a Multi-Layer ML-Based Security Framework for Industrial IoT},
  author={Bouferroum, Aymen and Loscri, Valeria and Benslimane, Abderrahim},
  journal={arXiv preprint arXiv:2603.24111},
  year={2026}
}

In Industrial IoT environments, trust management is vital for security, especially with resource-constrained devices, yet traditional trust models ignore fluctuating network quality, causing slow convergence and inaccurate assessments. We propose the Trust Convergence Acceleration (TCA) approach, which integrates a Random Forest model to predict the number of time units needed for trust convergence and dynamically adapts the transition probabilities of the trust model. On a simulation framework with realistic IEEE 802.11 (Wi-Fi 6) conditions, TCA cuts trust-convergence time by up to 28.6% under challenging conditions and improves trust-evaluation accuracy against malicious nodes.

@inproceedings{bouferroum2025accelerating,
  title={Accelerating Trust Convergence in IIoT: A ML Approach for Dynamic Network Conditions},
  author={Bouferroum, Aymen and Loscri, Valeria and Benslimane, Abderrahim},
  booktitle={IEEE Global Communications Conference (GLOBECOM) 2025},
  year={2025}
}

User-centric cell-free massive MIMO (UC-CFmMIMO) offers promising coverage for UAV communications but faces challenges in dynamic subband allocation. We propose a reinforcement-learning-driven framework that optimizes subband allocation for UAV users, adapting to varying trajectories and traffic demands to achieve near-optimal spectral efficiency at a fraction of the computational cost of exhaustive search.

@INPROCEEDINGS{11099147,
  author={Cheggour, Selina and Bouferroum, Aymen and Krishnan, Rahul},
  booktitle={2025 International Conference on Computer, Information and Telecommunication Systems (CITS)},
  title={Reinforcement Learning-Driven UC-CFmMIMO for UAVs: A Subband Allocation Framework},
  year={2025},
  volume={},
  number={},
  pages={1-8},
  keywords={6G mobile communication;Wireless communication;Reinforcement learning;Quality of service;Massive MIMO;Interference;Dynamic scheduling;Resource management;Vehicle dynamics;Radio spectrum management;Sixth-generation (6G);User-Centric Cell-Free Massive MIMO (UC-CFmMIMO);Aerial Vehicular Networks;Resource Allocation;Reinforcement Learning (RL);Deep Deterministic Policy Gradient (DDPG)},
  doi={10.1109/CITS65975.2025.11099147}}

The FITNESS project addresses the technical barriers preventing widespread IoT adoption in industrial and societal contexts. This paper presents the project vision and key insights on overcoming challenges of network heterogeneity, security, energy efficiency, and scalability, outlining the architectural principles developed within the French PEPR Future Networks program toward trustworthy, interoperable IoT.

@misc{cassiau2025fitness,
  author = {Cassiau, Nicolas and Achir, Nadjib and Adjih, Cédric and Andrieux, Guillaume and Bechkit, Walid and others},
  title  = {Overcoming the Technical Hurdles of IoT Adoption: the FITNESS Project Vision and Insights},
  year   = {2025},
  doi    = {10.5281/zenodo.17119689},
  note   = {hal-05257163},
  url    = {https://hal.science/hal-05257163}
}