Search papers, labs, and topics across Lattice.
This paper introduces PrivateHub, a contrastive diffusion model designed to generate synthetic multi-sensor data that balances the need for application inference with user privacy. By employing a two-stage approach鈥擜pp-Conditioned Pre-training (ACP) and App-Aware Fine-tuning (AAF)鈥攖he model effectively distinguishes between private and non-private applications, achieving a significant reduction in the accuracy of detecting private applications by 40 to 50% while maintaining non-private performance. The results demonstrate that PrivateHub can withstand adversarial retraining attempts, highlighting its robustness in protecting user privacy in sensor-intensive environments.
PrivateHub can reduce the accuracy of private application detection by up to 50% without sacrificing the performance of non-private applications.
Sensor-intensive environments enable many intelligent services by inferring user applications from heterogeneous data streams. However, not all applications should be exposed: users want some activities to stay private. This creates a tension between inferring applications for useful services and preventing unwanted inference. Existing approaches such as differential privacy and rule-based filtering protect individual streams but cannot address the privacy risk from cross-sensor inference. We introduce Privatehub, which uses contrastive learning within a diffusion model to generate synthetic multi-sensor streams that keep non-private applications detectable while concealing private ones. Privatehub has two stages: App-Conditioned Pre-training (ACP), which conditions the model on multi-sensor data with application embeddings, and App-Aware Fine-tuning (AAF), which separates private from non-private data via contrastive learning. We also define a threat model for the multi-sensor sharing setting. Experiments on three real-world multi-sensor datasets show Privatehub lowers private-application accuracy by 40 to 50\% without hurting non-private performance, and stays robust when the attacker retrains on the synthetic data.
