PSD 2024, Privacy in Statistical Databases Conference, 25-27 September 2024, Antibes, France / Also to be published in Lecture Notes in Computer Science (LNCS)
We present a stealthy privacy attack that exposes links in Graph Neural Networks (GNNs). Focusing on dynamic GNNs, we propose to inject new nodes and attach them to a particular target node to infer its private edge information. Our approach significantly enhances the F1 score of the attack compared to the current state-of-the-art benchmarks.
Specifically, for the Twitch dataset, our method improves the F1 score by 23.75%, and for the Flickr dataset, remarkably, it is more than three times better than the state-of-the-art. We also propose and evaluate defense strategies based on differentially private (DP) mechanisms relying on a newly defined DP notion. These solutions, on average, reduce
the effectiveness of the attack by 71.9% while only incurring a minimal utility loss of about 3.2%.
Type:
Conference
City:
Antibes
Date:
2024-09-27
Department:
Digital Security
Eurecom Ref:
7812
Copyright:
© Springer. Personal use of this material is permitted. The definitive version of this paper was published in PSD 2024, Privacy in Statistical Databases Conference, 25-27 September 2024, Antibes, France / Also to be published in Lecture Notes in Computer Science (LNCS) and is available at :
See also:
