MambaNetBurst: Direct Byte-level Network Traffic Classification without Tokenization or Pretraining

TL;DR

MambaNetBurst is a compact, tokenizer-free byte-level network traffic classifier that operates directly on raw packet bytes, achieving strong results without pre-training or tokenization.

Contribution

It introduces a novel byte-level classification method using Mamba-2 backbone, eliminating the need for tokenization and pre-training, and demonstrating effectiveness across multiple benchmarks.

Findings

Outperforms or matches heavier, pre-trained models on six benchmarks.

Preserving byte-level temporal resolution is critical for accuracy.

Moderate state sizes suffice for robust generalization.

Abstract

We present MambaNetBurst, a compact tokenizer-free byte-level sequence classifier for network burst classification based on a Mamba-2 backbone. In contrast to most recent strong traffic-classification and intrusion-detection approaches, our method operates directly on raw packet bytes, avoids tokenization, patching, and heavy engineered multimodal representations, and does not require any self-supervised pre-training stage. Given a packet flow, we form a fixed-length burst from the first few packets, embed the resulting byte sequence appending a learnable CLS token, and process it with a stack of residual pre-normalized Mamba-2 blocks for end-to-end supervised classification. Across six public benchmarks spanning encrypted mobile app identification, VPN/Tor traffic classification, malware traffic classification, and IoT attack traffic, MambaNetBurst achieves consistently strong results and is competitive with, or outperforms, substantially heavier and often pre-trained baselines. Our ablation study shows that preserving byte-level temporal resolution is critical, that early downsampling through striding is consistently harmful, and that moderate state sizes are sufficient for robust generalization. We further show that Mamba-2, despite its more constrained transition structure relative to Mamba-1, remains highly effective for packet-byte modeling while providing clear efficiency advantages, particularly in training speed. Overall, our results demonstrate that direct **undiluted** byte-to-classification learning with compact selective state space models is a practical, effective and novel direction for efficient, deployable traffic analysis that bypasses the complexity of pre-training pipelines even over highly optimized linear attention architectures.