Robust Locally Differentially Private Graph Analysis

Jacob Imola, Amrita Roy Chowdhury, Kamalika Chaudhuri

Keywords: Data poisoning, Local differential privacy, graphs.

TL;DR: We study the impact of poisoning attacks on graphs under local differential privacy.

Abstract: Locally differentially private (LDP) graph analysis allows private analysis on a graph that is distributed across multiple users. However, such computations are vulnerable to poisoning attacks where an adversary can skew the results by submitting malformed data. In this paper, we formally study the impact of poisoning attacks for graph degree estimation protocols under LDP. We make two key technical contributions. First, we observe LDP makes a protocol more vulnerable to poisoning – the impact of poisoning is worse when the adversary can directly poison their (noisy) responses, rather than their input data. Second, we observe that graph data is naturally redundant – every edge is shared between two users. Leveraging this data redundancy, we design robust degree estimation protocols under LDP that can significantly reduce the impact of poisoning and compute degree estimates with high accuracy. We prove that our robust protocols achieve the optimal levels of accuracy and soundness via information-theoretic lower bounds. Finally, we evaluate our proposed robust degree estimation protocols under poisoning attacks on real-world datasets to demonstrate their efficacy in practice.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 11088