Are We There Yet? Timing and Floating-Point Attacks on Differential Privacy Systems
Jiankai Jin, Eleanor McMurtry, Benjamin I. P. Rubinstein, Olga, Ohrimenko

TL;DR
This paper uncovers vulnerabilities in differential privacy implementations, demonstrating floating-point and timing attacks that can compromise privacy guarantees, and evaluates potential mitigations for these security flaws.
Contribution
It identifies and experimentally validates two new implementation flaws in DP systems—floating-point and timing side-channel attacks—and assesses their impact on privacy guarantees.
Findings
Floating-point attacks succeed against DP algorithms, including DP-SGD.
Timing attacks can predict noise magnitude, compromising privacy.
State-of-the-art DP implementations are vulnerable to these attacks.
Abstract
Differential privacy is a de facto privacy framework that has seen adoption in practice via a number of mature software platforms. Implementation of differentially private (DP) mechanisms has to be done carefully to ensure end-to-end security guarantees. In this paper we study two implementation flaws in the noise generation commonly used in DP systems. First we examine the Gaussian mechanism's susceptibility to a floating-point representation attack. The premise of this first vulnerability is similar to the one carried out by Mironov in 2011 against the Laplace mechanism. Our experiments show attack's success against DP algorithms, including deep learning models trained using differentially-private stochastic gradient descent. In the second part of the paper we study discrete counterparts of the Laplace and Gaussian mechanisms that were previously proposed to alleviate the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsPrivacy-Preserving Technologies in Data · Cryptography and Data Security · Stochastic Gradient Optimization Techniques
