Traffic classification is crucial for securing Internet of Things (IoT) networks. Deep learning-based methods can autonomously extract latent patterns from massive network traffic, demonstrating significant potential for IoT traffic classification tasks. However, the limited computational and spatial resources of IoT devices pose challenges for deploying more complex deep learning models. Existing methods rely heavily on either flow-level features or raw packet byte features. Flow-level features often require inspecting entire or most of the traffic flow, leading to excessive resource consumption, while raw packet byte features fail to distinguish between headers and payloads, overlooking semantic differences and introducing noise from feature misalignment. Therefore, this paper proposes IoT-AMLHP, an aligned multimodal learning framework for resource-efficient malicious IoT traffic classification. Firstly, the framework constructs a packet-wise header-payload representation by parsing packet headers and payload bytes, resulting in an aligned and standardized multimodal traffic representation that enhances the characterization of heterogeneous IoT traffic. Subsequently, the traffic representation is fed into a resource-efficient neural network comprising a multimodal feature extraction module and a multimodal fusion module. The extraction module employs efficient depthwise separable convolutions to capture multi-scale features from different modalities while maintaining a lightweight architecture. The fusion module adaptively captures complementary features from different modalities and effectively fuses multimodal features.

翻译：流量分类对于保障物联网网络的安全至关重要。基于深度学习的方法能够从海量网络流量中自主提取潜在模式，在物联网流量分类任务中展现出巨大潜力。然而，物联网设备有限的计算和存储资源为部署更复杂的深度学习模型带来了挑战。现有方法严重依赖于流级特征或原始数据包字节特征。流级特征通常需要检查整个或大部分流量流，导致资源消耗过高；而原始数据包字节特征无法区分头部与载荷，忽视了语义差异并因特征未对齐而引入噪声。为此，本文提出物联网-AMLHP，一种用于资源高效恶意物联网流量分类的对齐多模态学习框架。首先，该框架通过解析数据包头和载荷字节构建逐包头部-载荷表示，形成对齐且标准化的多模态流量表示，从而增强对异构物联网流量的表征能力。随后，该流量表示被输入一个由多模态特征提取模块和多模态融合模块组成的资源高效神经网络。提取模块采用高效的深度可分离卷积从不同模态中捕获多尺度特征，同时保持轻量级架构。融合模块自适应地捕获来自不同模态的互补特征，并有效地融合多模态特征。