Dynamic User-controllable Privacy-preserving Few-shot Sensing Framework

TL;DR

PrivCLIP is a novel framework that enables user-controlled, dynamic privacy preservation in sensor data by using multimodal contrastive learning and language-guided data transformation, allowing few-shot adaptation to individual privacy preferences.

Contribution

This work introduces PrivCLIP, a flexible, user-controllable privacy-preserving sensing system that leverages multimodal contrastive learning and language-guided data sanitization for the first time.

Findings

PrivCLIP outperforms baseline methods in privacy protection.

The framework maintains high data utility for non-sensitive activities.

PrivCLIP adapts effectively with few-shot learning for user-specific privacy preferences.

Abstract

User-controllable privacy is important in modern sensing systems, as privacy preferences can vary significantly from person to person and may evolve over time. This is especially relevant in devices equipped with Inertial Measurement Unit (IMU) sensors, such as smartphones and wearables, which continuously collect rich time-series data that can inadvertently expose sensitive user behaviors. While prior work has proposed privacy-preserving methods for sensor data, most rely on static, predefined privacy labels or require large quantities of private training data, limiting their adaptability and user agency. In this work, we introduce PrivCLIP, a dynamic, user-controllable, few-shot privacy-preserving sensing framework. PrivCLIP allows users to specify and modify their privacy preferences by categorizing activities as sensitive (black-listed), non-sensitive (white-listed), or neutral (gray-listed). Leveraging a multimodal contrastive learning approach, PrivCLIP aligns IMU sensor data with natural language activity descriptions in a shared embedding space, enabling few-shot detection of sensitive activities. When a privacy-sensitive activity is identified, the system uses a language-guided activity sanitizer and a motion generation module (IMU-GPT) to transform the original data into a privacy-compliant version that semantically resembles a non-sensitive activity. We evaluate PrivCLIP on multiple human activity recognition datasets and demonstrate that it significantly outperforms baseline methods in terms of both privacy protection and data utility.