Balancing Trade-offs: Adaptive Differential Privacy in Interpretable Machine Learning Models

Conference · Fri Aug 01 00:00:00 EDT 2025

DOI:https://doi.org/10.1109/PST65910.2025.11268818· OSTI ID:3015572

Farhad Riya, Farhin ^[1]; Hoque, Shahinul ^[1]; Yang, Yingyuan ^[2]; Sun, Jinyuan ^[1]; Kotevska, Olivera ^[3]

---

1. University of Tennessee, Knoxville (UTK)
2. University of Illinois
3. ORNL

In the advancing field of machine learning, balancing accuracy, interpretability, and privacy represents a significant challenge. The problem is exacerbated by the widespread deployment of pre-trained models locally in diverse applications, which could lead to various amounts of privacy leakage. Conventional Differential Privacy strategies, in which uniform noises are applied to model gradients, guarantee data privacy at the expense of accuracy and interpretability. This paper introduces a Feature-Sensitive Adaptive Differential Privacy (FADP) framework with a unique noise-adding strategy. Noises are adaptively added based on feature importance clustering, where important features are considered for interpretability. By employing a unique masking technique, FADP selectively preserves crucial features with minimal noise interference, maintaining accuracy while enhancing interpretability. The FADP framework addresses the limitations of traditional DP methods by preserving critical channels and improving interpretability — a vital requirement in machine learning applications that demand transparency in model decisions. Through comprehensive testing, FADP is shown to balance the trade-offs among accuracy, privacy, and interpretability, marking a substantial advancement in the field of privacy-preserving machine learning.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 3015572
• Resource Type: Conference paper/presentation
• Conference Information: 22nd Annual International Conference on Privacy, Security, and Trust (PST2025) - Fredericton, Canada - 8/26/2025-8/28/2025
• Country of Publication: United States
• Language: English