Differentially Private Deep Learning with Smooth Sensitivity
This work addresses privacy concerns for sensitive data in machine learning, offering a solution that enhances both performance and privacy guarantees, though it appears incremental as it builds on existing teacher-student frameworks.
The paper tackles the trade-off between model performance and privacy in differentially private deep learning by proposing a novel voting mechanism called Immutable Noisy ArgMax with smooth sensitivity, which improves state-of-the-art methods across all measures and scales to larger tasks with better performance and stronger privacy (ε ≈ 0).
Ensuring the privacy of sensitive data used to train modern machine learning models is of paramount importance in many areas of practice. One approach to study these concerns is through the lens of differential privacy. In this framework, privacy guarantees are generally obtained by perturbing models in such a way that specifics of data used to train the model are made ambiguous. A particular instance of this approach is through a "teacher-student" framework, wherein the teacher, who owns the sensitive data, provides the student with useful, but noisy, information, hopefully allowing the student model to perform well on a given task without access to particular features of the sensitive data. Because stronger privacy guarantees generally involve more significant perturbation on the part of the teacher, deploying existing frameworks fundamentally involves a trade-off between student's performance and privacy guarantee. One of the most important techniques used in previous works involves an ensemble of teacher models, which return information to a student based on a noisy voting procedure. In this work, we propose a novel voting mechanism with smooth sensitivity, which we call Immutable Noisy ArgMax, that, under certain conditions, can bear very large random noising from the teacher without affecting the useful information transferred to the student. Compared with previous work, our approach improves over the state-of-the-art methods on all measures, and scale to larger tasks with both better performance and stronger privacy ($ε\approx 0$). This new proposed framework can be applied with any machine learning models, and provides an appealing solution for tasks that requires training on a large amount of data.