Kusumastuti, Aurelia FarikhaAurelia FarikhaKusumastutiRangelov, DenisDenisRangelovLämmel, PhilippPhilippLämmelBoerger, MichellMichellBoergerAleksandrov, AndreiAndreiAleksandrovTcholtchev, Nikolay VassilevNikolay VassilevTcholtchev2025-07-162025-07-162025https://publica.fraunhofer.de/handle/publica/48960110.5220/0013637600003967This paper presents an exploratory analysis of deep learning techniques for intrusion detection in IoT networks. Specifically, we investigate three innovative intrusion detection systems based on transformer, 1D-CNN and GrowNet architectures, comparing their performance against random forest and three-layer perceptron models as baselines. For each model, we study the multiclass classification performance using the publicly available IoT network traffic dataset Bot-IoT. We use the most important performance indicators, namely, accuracy, F1-score, and ROC, but also training and inference time to gauge the utility and efficacy of the models. In contrast to earlier studies where random forests were the dominant method for ML-based intrusion detection, our findings indicate that the transformer architecture outperforms all other methods in our approach.enTransformerRandom ForestDeep Neural NetworksCNNAnomaly DetectionIntrusion DetectionIoTconference paper