CLOAK: Contrastive Guidance for Latent Diffusion-Based Data Obfuscation

TL;DR

Cloak introduces a contrastive-guided latent diffusion framework for data obfuscation that effectively balances privacy and utility, outperforming existing methods and suitable for resource-limited devices.

Contribution

This work presents a novel contrastive learning approach integrated with latent diffusion models for data obfuscation, enhancing privacy-utility trade-offs without extensive retraining.

Findings

Outperforms state-of-the-art obfuscation techniques across multiple datasets

Effective in resource-constrained mobile IoT environments

Provides customizable privacy levels with minimal retraining

Abstract

Data obfuscation is a promising technique for mitigating attribute inference attacks by semi-trusted parties with access to time-series data emitted by sensors. Recent advances leverage conditional generative models together with adversarial training or mutual information-based regularization to balance data privacy and utility. However, these methods often require modifying the downstream task, struggle to achieve a satisfactory privacy-utility trade-off, or are computationally intensive, making them impractical for deployment on resource-constrained mobile IoT devices. We propose Cloak, a novel data obfuscation framework based on latent diffusion models. In contrast to prior work, we employ contrastive learning to extract disentangled representations, which guide the latent diffusion process to retain useful information while concealing private information. This approach enables users with diverse privacy needs to navigate the privacy-utility trade-off with minimal retraining. Extensive experiments on four public time-series datasets, spanning multiple sensing modalities, and a dataset of facial images demonstrate that Cloak consistently outperforms state-of-the-art obfuscation techniques and is well-suited for deployment in resource-constrained settings.