End-to-End triplet loss based fine-tuning for network embedding in effective PII detection

TL;DR

This paper introduces an end-to-end deep learning framework utilizing triplet loss and large language models to improve detection of personally identifiable information leaks in mobile network traffic.

Contribution

It presents a novel triplet-loss based fine-tuning approach combined with LLM and autoencoders for PII detection, eliminating the need for external feature selection.

Findings

Enhanced detection accuracy on real-world datasets

Outperforms existing state-of-the-art methods

Effective in identifying PII leaks from mobile network traffic

Abstract

There are many approaches in mobile data ecosystem that inspect network traffic generated by applications running on user's device to detect personal data exfiltration from the user's device. State-of-the-art methods rely on features extracted from HTTP requests and in this context, machine learning involves training classifiers on these features and making predictions using labelled packet traces. However, most of these methods include external feature selection before model training. Deep learning, on the other hand, typically does not require such techniques, as it can autonomously learn and identify patterns in the data without external feature extraction or selection algorithms. In this article, we propose a novel deep learning based end-to-end learning framework for prediction of exposure of personally identifiable information (PII) in mobile packets. The framework employs a pre-trained large language model (LLM) and an autoencoder to generate embedding of network packets and then uses a triplet-loss based fine-tuning method to train the model, increasing detection effectiveness using two real-world datasets. We compare our proposed detection framework with other state-of-the-art works in detecting PII leaks from user's device.