Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Weaknesses and Attack Patterns Prediction for IoT Devices

Carlos A. Rivera A., Arash Shaghaghi, Gustavo Batista, Salil S. Kanhere

TL;DR

A cost-efficient platform to facilitate the pre-deployment security checks of IoT devices by predicting potential weaknesses and associated attack patterns by employing a Bidirectional Long Short-Term Memory network and a Gradient Boosting Machine model.

Abstract

As the adoption of Internet of Things (IoT) devices continues to rise in enterprise environments, the need for effective and efficient security measures becomes increasingly critical. This paper presents a cost-efficient platform to facilitate the pre-deployment security checks of IoT devices by predicting potential weaknesses and associated attack patterns. The platform employs a Bidirectional Long Short-Term Memory (Bi-LSTM) network to analyse device-related textual data and predict weaknesses. At the same time, a Gradient Boosting Machine (GBM) model predicts likely attack patterns that could exploit these weaknesses. When evaluated on a dataset curated from the National Vulnerability Database (NVD) and publicly accessible IoT data sources, the system demonstrates high accuracy and reliability. The dataset created for this solution is publicly accessible.

Towards Weaknesses and Attack Patterns Prediction for IoT Devices

TL;DR

A cost-efficient platform to facilitate the pre-deployment security checks of IoT devices by predicting potential weaknesses and associated attack patterns by employing a Bidirectional Long Short-Term Memory network and a Gradient Boosting Machine model.

Abstract

As the adoption of Internet of Things (IoT) devices continues to rise in enterprise environments, the need for effective and efficient security measures becomes increasingly critical. This paper presents a cost-efficient platform to facilitate the pre-deployment security checks of IoT devices by predicting potential weaknesses and associated attack patterns. The platform employs a Bidirectional Long Short-Term Memory (Bi-LSTM) network to analyse device-related textual data and predict weaknesses. At the same time, a Gradient Boosting Machine (GBM) model predicts likely attack patterns that could exploit these weaknesses. When evaluated on a dataset curated from the National Vulnerability Database (NVD) and publicly accessible IoT data sources, the system demonstrates high accuracy and reliability. The dataset created for this solution is publicly accessible.
Paper Structure (13 sections, 6 equations, 3 figures, 9 tables)

This paper contains 13 sections, 6 equations, 3 figures, 9 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Proposed Solution
  4. Dataset for Weakness Prediction Framework
  5. Model Selection
  6. Experimental Setup & Implementation
  7. Evaluation Results
  8. Multi-Class Multi-Label Implementation
  9. Dataset for Attack Patterns Prediction Framework
  10. Model Selection
  11. Experimental Setup and Evaluation for Attack Patterns Prediction Framework
  12. Conclusion and Future Work
  13. Dataset

Figures (3)

  • Figure 1: Accuracy, Train Loss, and Test Loss from training 1K-epochs the Bi-LSTM model over the OI V1.1 dataset.
  • Figure 2: Confusion matrix from the Bi-LSTM model and from loading the 1K epoch on the OI V1.1 dataset test.
  • Figure 3: Mapping between APT Kill Chain, Types of Attack Classes, and CAPECs from Mechanisms of Attack View.