Enhancing ECA (Event- Condition-Action) Rules: Fine-Tuning BERT for Security and Privacy Violation Detection

Abstract

In the world of Internet of Things, Event Condition Action rules are the secret sauce for smart device interaction. An Event triggers the rule. If a specific Condition is met, then an Action happens automatically. This article addresses trigger–action platforms, which empower users to define custom behaviors for IoT devices and web services through conditional rules. While these platforms enhance user creativity in automation, they also pose significant risks, such as unintentional disclosure of private information or exposure to cyber threats. The proposed solution leverages Natural Language Processing techniques to identify automation rules within these platforms that may compromise user security or privacy. Natural Language Processing based models are applied to analyze the semantic and contextual information of trigger–action rules, utilizing classification techniques on various rule features. Evaluation on the If-This-Then-That platform, using a dataset of 76,741 rules labeled through an ensemble of three semi-supervised learning techniques, demonstrates that the results from the Bidirectional Encoder Representations from Transformers based model training demonstrate promising outcomes, with an average validation accuracy of 89% over 2 epochs. The Test Accuracy of around 90.65% is achieved. Predicted outputs showcase the model's ability to categorize applets into different risk classes, including instances of cyber security threats and physical harm.