LDP-Slicing: Local Differential Privacy for Images via Randomized Bit-Plane Slicing
This work addresses the problem of privacy-preserving machine learning for image data, which is crucial for applications where sensitive visual information is involved, such as healthcare or surveillance, and provides an incremental yet significant improvement over existing methods.
The authors tackled the problem of applying Local Differential Privacy (LDP) to high-dimensional image data, achieving a significant reduction in utility loss, and demonstrated that their approach, LDP-Slicing, outperforms existing DP/LDP baselines with negligible computational overhead. LDP-Slicing retains high utility for downstream tasks such as face recognition and image classification.
Local Differential Privacy (LDP) is the gold standard trust model for privacy-preserving machine learning by guaranteeing privacy at the data source. However, its application to image data has long been considered impractical due to the high dimensionality of pixel space. Canonical LDP mechanisms are designed for low-dimensional data, resulting in severe utility degradation when applied to high-dimensional pixel spaces. This paper demonstrates that this utility loss is not inherent to LDP, but from its application to an inappropriate data representation. We introduce LDP-Slicing, a lightweight, training-free framework that resolves this domain mismatch. Our key insight is to decompose pixel values into a sequence of binary bit-planes. This transformation allows us to apply the LDP mechanism directly to the bit-level representation. To further strengthen privacy and preserve utility, we integrate a perceptual obfuscation module that mitigates human-perceivable leakage and an optimization-based privacy budget allocation strategy. This pipeline satisfies rigorous pixel-level $\varepsilon$-LDP while producing images that retain high utility for downstream tasks. Extensive experiments on face recognition and image classification demonstrate that LDP-Slicing outperforms existing DP/LDP baselines under comparable privacy budgets, with negligible computational overhead.