LUT-Compiled Kolmogorov-Arnold Networks for Lightweight DoS Detection on IoT Edge Devices
Oleksandr Kuznetsov

TL;DR
This paper introduces LUT-compiled Kolmogorov-Arnold Networks (KANs) for efficient, real-time DoS attack detection on resource-limited IoT edge devices, significantly reducing inference latency while maintaining high accuracy.
Contribution
The authors develop a LUT compilation pipeline for KANs, enabling fast, accurate DoS detection on IoT devices with minimal resource usage and deterministic latency.
Findings
Achieves 99.0% accuracy on CICIDS2017 dataset.
Provides 68x speedup at batch size 256 with only 2x memory overhead.
Maintains near-original accuracy after LUT compilation with high resolution.
Abstract
Denial-of-Service (DoS) attacks pose a critical threat to Internet of Things (IoT) ecosystems, yet deploying effective intrusion detection on resource-constrained edge devices remains challenging. Kolmogorov-Arnold Networks (KANs) offer a compact alternative to Multi-Layer Perceptrons (MLPs) by placing learnable univariate spline functions on edges rather than fixed activations on nodes, achieving competitive accuracy with fewer parameters. However, runtime B-spline evaluation introduces significant computational overhead unsuitable for latency-critical IoT applications. We propose a lookup table (LUT) compilation pipeline that replaces expensive spline computations with precomputed quantized tables and linear interpolation, dramatically reducing inference latency while preserving detection quality. Our lightweight KAN model (50K parameters, 0.19~MB) achieves 99.0\% accuracy on the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNetwork Security and Intrusion Detection · IoT and Edge/Fog Computing · Software-Defined Networks and 5G
