TADP-RME: A Trust-Adaptive Differential Privacy Framework for Enhancing Reliability of Data-Driven Systems
This work addresses reliability issues in adversarial environments for data-driven systems, offering an incremental improvement over existing differential privacy methods.
The paper tackled the problem of rigid utility-privacy trade-offs in data-driven systems under heterogeneous user trust by proposing TADP-RME, which adaptively modulates privacy budgets and disrupts geometric structures, resulting in reduced attack success rates by up to 3.1% without significant utility degradation.
Ensuring reliability in adversarial settings necessitates treating privacy as a foundational component of data-driven systems. While differential privacy and cryptographic protocols offer strong guarantees, existing schemes rely on a fixed privacy budget, leading to a rigid utility-privacy trade-off that fails under heterogeneous user trust. Moreover, noise-only differential privacy preserves geometric structure, which inference attacks exploit, causing privacy leakage. We propose TADP-RME (Trust-Adaptive Differential Privacy with Reverse Manifold Embedding), a framework that enhances reliability under varying levels of user trust. It introduces an inverse trust score in the range [0,1] to adaptively modulate the privacy budget, enabling smooth transitions between utility and privacy. Additionally, Reverse Manifold Embedding applies a nonlinear transformation to disrupt local geometric relationships while preserving formal differential privacy guarantees through post-processing. Theoretical and empirical results demonstrate improved privacy-utility trade-offs, reducing attack success rates by up to 3.1 percent without significant utility degradation. The framework consistently outperforms existing methods against inference attacks, providing a unified approach for reliable learning in adversarial environments.