Long-term Data Sharing under Exclusivity Attacks

TL;DR

This paper investigates the vulnerability of long-term data sharing protocols to exclusivity attacks, where malicious entities can distort shared data to mislead others while optimizing their own models.

Contribution

It analyzes the impact of protocol design and Sybil attacks on data sharing security for regression and clustering tasks, providing insights into mitigating vulnerabilities.

Findings

Protocol choice affects vulnerability to exclusivity attacks.

Number of Sybil identities influences attack success.

Certain protocols are more resilient to data distortion attacks.

Abstract

The quality of learning generally improves with the scale and diversity of data. Companies and institutions can therefore benefit from building models over shared data. Many cloud and blockchain platforms, as well as government initiatives, are interested in providing this type of service. These cooperative efforts face a challenge, which we call ``exclusivity attacks''. A firm can share distorted data, so that it learns the best model fit, but is also able to mislead others. We study protocols for long-term interactions and their vulnerability to these attacks, in particular for regression and clustering tasks. We conclude that the choice of protocol, as well as the number of Sybil identities an attacker may control, is material to vulnerability.