Recent deep learning approaches for network intrusion detection increasingly incorporate temporal architectures such as recurrent networks and Transformers, often reporting near-perfect performance on CIC-IDS2017. However, many existing studies neither supply their temporal modules with genuine sequence inputs nor evaluate under realistic, leakage-free conditions, making it unclear whether reported gains arise from true sequence-modeling capability.
arXiv:2609.36039v1 Announce Type: cross
Abstract: Machine learning (ML) and deep learning (DL) have dominated Intrusion Detection System (IDS) research in recent years. Unfortunately, many existing s...
By Yufeng Xin, Bryant Goseland, Mohamed Rahouti
The study compares XGBoost and RoBERTa‑LoRA for network intrusion detection across three evaluation axes: same‑dataset performance, cross‑dataset transfer, and adversarial evasion. Both models perform similarly on the same dataset, but XGBoost outperforms RoBERTa‑LoRA by 15 F1 points and 25 balanced accuracy points when transferred to a different network, while RoBERTa‑LoRA wins by about 17 F1 points under adversarial evasion. Feature‑leakage ablation shows that cross‑dataset transfer improvements are non‑monotonic and directional, suggesting leakage is spread across features rather than isolated.
"whyItMatters":"The findings demonstrate that a model’s superiority depends on the specific robustness axis evaluated, underscoring the need for multi‑axis, multi‑metric testing in network intrusion detection research."
By Muhammad Ebad Atif, Muhammad Haider Ali
arXiv:2606. 01442v1 Announce Type: cross Abstract: Network intrusion detection is a core component of modern cybersecurity infrastructure, yet the deep learning models that dominate the field are computationally demanding, motivating interest in lightweight alternatives suited to edge and neuromorphic deployment.
By Raj Patel, David Amebley, Taye Akinrele, Shaswata Mitra, Sayanton Dibbo, Shahram Rahimi
The paper investigates whether machine learning models for IoT intrusion detection truly learn attack patterns or rely on dataset shortcuts. Using the CyberFlowIoT-GICAP benchmark, the authors evaluate four learning paradigms across different feature sets and split strategies, finding that performance is largely driven by feature representation and that tree-based models can exploit temporal artifacts. The study also highlights asymmetric attack detectability and proposes a four-point protocol checklist for realistic evaluation.
By Uday Shankar Roy, Mahbuba Jahan Minu
arXiv:2606.01442v2 Announce Type: replace-cross
Abstract: Spiking neural networks (SNNs) are increasingly studied for network intrusion detection, but comparative evidence on how neuron models and sp...
By Raj Patel, Shaswata Mitra, David Amebley, Taye Akinrele, Sayanton Dibbo, Shahram Rahimi