article
Internet of Things devices face growing risks from large-scale cyberattacks, yet existing intrusion detection systems remain largely reactive by responding only after observing anomalies or set patterns. To address this vulnerability, a proactive network intrusion prediction framework integrates large language models with long short-term memory networks. The system operates via a feedback loop featuring two specialised models: a fine-tuned Generative Pre-trained Transformer predicts forthcoming network traffic, while a fine-tuned Bidirectional Encoder Representations from Transformers evaluates that predicted traffic. A long short-term memory classifier then analyses the generated traffic predictions to identify malicious packets before damage occurs. Evaluated on the benchmark CICIoT2023 dataset, the framework reached an overall prediction accuracy of 98 percent, demonstrating a viable approach for anticipating emerging cyber threats across connected device networks.
As billions of connected devices integrate into daily life and industry, securing them against cyberattacks becomes vital. Traditional systems catch threats only after network intrusion begins, leaving systems vulnerable to harm. Moving from reactive detection to predictive anticipation allows network operators to stop attacks before they cause operational disruption, data loss, or physical damage in critical Internet of Things infrastructure.
This framework could support proactive cybersecurity software designed for enterprise and industrial Internet of Things networks. Network operators and security vendors could utilise such predictive tools to prevent cyber intrusions before they compromise hardware. Because the method has been validated on a standard benchmark dataset rather than deployed in live production environments, it currently represents an applied and tested research prototype requiring further live network trials.
AI-generated from the published abstract. Always read the original work before citing.
In recent years, numerous large-scale cyberattacks have exploited Internet of Things (IoT) devices, a phenomenon that is expected to escalate with the continuing proliferation of IoT technology. Despite considerable efforts in attack detection, intrusion detection systems remain mostly reactive, responding to specific patterns or observed anomalies. This work proposes a proactive approach to anticipate and mitigate malicious activities before they cause damage. This paper proposes a novel network intrusion prediction framework that combines Large Language Models (LLMs) with Long Short Term Memory (LSTM) networks. The framework incorporates two LLMs in a feedback loop: a fine-tuned Generative Pre-trained Transformer (GPT) model for predicting network traffic and a fine-tuned Bidirectional Encoder Representations from Transformers (BERT) for evaluating the predicted traffic. The LSTM classifier model then identifies malicious packets among these predictions. Our framework, evaluated on the CICIoT2023 IoT attack dataset, demonstrates a significant improvement in predictive capabilities, achieving an overall accuracy of 98%, offering a robust solution to IoT cybersecurity challenges.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/dcoss-iot61029.2024.00026
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
