SAFE-TAP: Semantic-aware and fused embedding for TAP rule security detection

Trigger-Action Programming (TAP) has emerged as a widely adopted paradigm for enabling automated interoperability among IoT devices. Despite its convenience, TAP introduces significant security vulnerabilities. To address this issue, we propose SAFE-TAP, a novel framework for detecting malicious TAP...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Neurocomputing (Amsterdam) Ročník 656; s. 131529
Hlavní autori: Kuang, Zhejun, Zhu, Yusheng, Sun, Dawen, Zhao, Jian, Xing, Yongheng, Wang, Feng, Sun, Lei
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 01.12.2025
Predmet:
IFTTT
Internet of things
Natural language processing (NLP)
Security detection
Trigger-action programming
Internet of things
IFTTT
Natural language processing (NLP)
Trigger-action programming
Security detection
ISSN:0925-2312
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Trigger-Action Programming (TAP) has emerged as a widely adopted paradigm for enabling automated interoperability among IoT devices. Despite its convenience, TAP introduces significant security vulnerabilities. To address this issue, we propose SAFE-TAP, a novel framework for detecting malicious TAP rules that integrates global semantic understanding with temporal feature analysis. To further enhance the detection performance, we introduce an innovative data augmentation strategy that leverages Large Language Models (LLMs) to generate semantically consistent rule variations. This approach improves data set balance and enhances the generalizability of the model. Experimental results demonstrate that SAFE-TAP outperforms baseline methods, and the incorporation of LLM-based data augmentation significantly improves detection performance under imbalanced data scenarios.
ISSN:0925-2312
DOI:10.1016/j.neucom.2025.131529