Proactive Detection of Physical Inter-rule Vulnerabilities in IoT Services Using a Deep Learning Approach

TL;DR

This work tackles the problem of physical inter-rule vulnerabilities in IoT TAP systems by proposing a proactive, design-stage framework. It combines a Transformer-based rule extractor to convert natural-language descriptions into trigger-action rules, an NLP component (via ChatGPT-4) to identify environment channels, and a formal vulnerability detector to uncover Environment Channel Rule Chain and Environment Channel Interference scenarios among extracted rules. Experiments on 27,983 IFTTT rules yield 95.22% rule-extraction accuracy, while analysis of 60 SmartThings apps reveals 99 vulnerabilities, with 60.6% being chains. The approach demonstrates how early, automated detection can reduce the risk of unsafe or conflicting IoT configurations in smart homes and informs future risk assessment and user-preference considerations for resolving vulnerabilities.

Abstract

Emerging Internet of Things (IoT) platforms provide sophisticated capabilities to automate IoT services by enabling occupants to create trigger-action rules. Multiple trigger-action rules can physically interact with each other via shared environment channels, such as temperature, humidity, and illumination. We refer to inter-rule interactions via shared environment channels as a physical inter-rule vulnerability. Such vulnerability can be exploited by attackers to launch attacks against IoT systems. We propose a new framework to proactively discover possible physical inter-rule interactions from user requirement specifications (i.e., descriptions) using a deep learning approach. Specifically, we utilize the Transformer model to generate trigger-action rules from their associated descriptions. We discover two types of physical inter-rule vulnerabilities and determine associated environment channels using natural language processing (NLP) tools. Given the extracted trigger-action rules and associated environment channels, an approach is proposed to identify hidden physical inter-rule vulnerabilities among them. Our experiment on 27983 IFTTT style rules shows that the Transformer can successfully extract trigger-action rules from descriptions with 95.22% accuracy. We also validate the effectiveness of our approach on 60 SmartThings official IoT apps and discover 99 possible physical inter-rule vulnerabilities.

Figures (3)

• Figure 1: Overview of the proposed framework
• Figure 2: Extracting IoT rules from descriptions
• Figure 3: The architecture of the Transformer model.