Detecting Attacks on IoT Devices using Featureless 1D-CNN

TL;DR

This paper proposes a featureless 1D-CNN approach for anomaly detection in IoT devices, reducing the need for feature engineering and enabling low-cost, low-memory network traffic analysis.

Contribution

It introduces a novel featureless machine learning method using unprocessed byte streams with 1D-CNNs for IoT anomaly detection, simplifying the process and reducing resource requirements.

Findings

Enables anomaly detection without feature engineering.

Reduces memory and processing needs for IoT security.

Facilitates low-cost, real-time network analysis.

Abstract

The generalization of deep learning has helped us, in the past, address challenges such as malware identification and anomaly detection in the network security domain. However, as effective as it is, scarcity of memory and processing power makes it difficult to perform these tasks in Internet of Things (IoT) devices. This research finds an easy way out of this bottleneck by depreciating the need for feature engineering and subsequent processing in machine learning techniques. In this study, we introduce a Featureless machine learning process to perform anomaly detection. It uses unprocessed byte streams of packets as training data. Featureless machine learning enables a low cost and low memory time-series analysis of network traffic. It benefits from eliminating the significant investment in subject matter experts and the time required for feature engineering.