One Size Fits All? A Modular Adaptive Sanitization Kit (MASK) for Customizable Privacy-Preserving Phone Scam Detection

TL;DR

This paper introduces MASK, a flexible framework using modular sanitization techniques to enable privacy-preserving phone scam detection with large language models, allowing personalized privacy settings without sacrificing detection accuracy.

Contribution

The work presents a novel, extensible architecture that integrates diverse sanitization methods for privacy-aware LLM-based phone scam detection, adaptable to individual user preferences.

Findings

Proposes a pluggable architecture for privacy-preserving detection.

Enables dynamic privacy adjustment based on user preferences.

Discusses modeling approaches for personalized privacy-utility trade-offs.

Abstract

Phone scams remain a pervasive threat to both personal safety and financial security worldwide. Recent advances in large language models (LLMs) have demonstrated strong potential in detecting fraudulent behavior by analyzing transcribed phone conversations. However, these capabilities introduce notable privacy risks, as such conversations frequently contain sensitive personal information that may be exposed to third-party service providers during processing. In this work, we explore how to harness LLMs for phone scam detection while preserving user privacy. We propose MASK (Modular Adaptive Sanitization Kit), a trainable and extensible framework that enables dynamic privacy adjustment based on individual preferences. MASK provides a pluggable architecture that accommodates diverse sanitization methods - from traditional keyword-based techniques for high-privacy users to sophisticated neural approaches for those prioritizing accuracy. We also discuss potential modeling approaches and loss function designs for future development, enabling the creation of truly personalized, privacy-aware LLM-based detection systems that balance user trust and detection effectiveness, even beyond phone scam context.