Saved in:
Bibliographic Details
Main Authors: Goldberg, Alexander, Fanti, Giulia, Shah, Nihar, Wu, Zhiwei Steven
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.22347
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913965779451904
author Goldberg, Alexander
Fanti, Giulia
Shah, Nihar
Wu, Zhiwei Steven
author_facet Goldberg, Alexander
Fanti, Giulia
Shah, Nihar
Wu, Zhiwei Steven
contents We introduce the novel problem of benchmarking fraud detectors on private graph-structured data. Currently, many types of fraud are managed in part by automated detection algorithms that operate over graphs. We consider the scenario where a data holder wishes to outsource development of fraud detectors to third parties (e.g., vendors or researchers). The third parties submit their fraud detectors to the data holder, who evaluates these algorithms on a private dataset and then publicly communicates the results. We propose a realistic privacy attack on this system that allows an adversary to de-anonymize individuals' data based only on the evaluation results. In simulations of a privacy-sensitive benchmark for facial recognition algorithms by the National Institute of Standards and Technology (NIST), our attack achieves near perfect accuracy in identifying whether individuals' data is present in a private dataset, with a True Positive Rate of 0.98 at a False Positive Rate of 0.00. We then study how to benchmark algorithms while satisfying a formal differential privacy (DP) guarantee. We empirically evaluate two classes of solutions: subsample-and-aggregate and DP synthetic graph data. We demonstrate through extensive experiments that current approaches do not provide utility when guaranteeing DP. Our results indicate that the error arising from DP trades off between bias from distorting graph structure and variance from adding random noise. Current methods lie on different points along this bias-variance trade-off, but more complex methods tend to require high-variance noise addition, undermining utility.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22347
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Benchmarking Fraud Detectors on Private Graph Data
Goldberg, Alexander
Fanti, Giulia
Shah, Nihar
Wu, Zhiwei Steven
Cryptography and Security
We introduce the novel problem of benchmarking fraud detectors on private graph-structured data. Currently, many types of fraud are managed in part by automated detection algorithms that operate over graphs. We consider the scenario where a data holder wishes to outsource development of fraud detectors to third parties (e.g., vendors or researchers). The third parties submit their fraud detectors to the data holder, who evaluates these algorithms on a private dataset and then publicly communicates the results. We propose a realistic privacy attack on this system that allows an adversary to de-anonymize individuals' data based only on the evaluation results. In simulations of a privacy-sensitive benchmark for facial recognition algorithms by the National Institute of Standards and Technology (NIST), our attack achieves near perfect accuracy in identifying whether individuals' data is present in a private dataset, with a True Positive Rate of 0.98 at a False Positive Rate of 0.00. We then study how to benchmark algorithms while satisfying a formal differential privacy (DP) guarantee. We empirically evaluate two classes of solutions: subsample-and-aggregate and DP synthetic graph data. We demonstrate through extensive experiments that current approaches do not provide utility when guaranteeing DP. Our results indicate that the error arising from DP trades off between bias from distorting graph structure and variance from adding random noise. Current methods lie on different points along this bias-variance trade-off, but more complex methods tend to require high-variance noise addition, undermining utility.
title Benchmarking Fraud Detectors on Private Graph Data
topic Cryptography and Security
url https://arxiv.org/abs/2507.22347