The Conundrum of Trustworthy Research on Attacking Personally Identifiable Information Removal Techniques

TL;DR

This paper critically examines the effectiveness of PII removal techniques in protecting privacy, revealing that current evaluations are flawed due to data leakage issues and highlighting the challenges in objectively assessing privacy protection.

Contribution

It provides a critical analysis of existing attack evaluations on PII removal, identifying key flaws and proposing the need for private data access for trustworthy assessment.

Findings

Existing attack evaluations are often flawed due to data leakage.

Proper assessment requires access to private data, which is heavily restricted.

Current methods may overestimate the vulnerability of PII removal techniques.

Abstract

Removing personally identifiable information (PII) from texts is necessary to comply with various data protection regulations and to enable data sharing without compromising privacy. However, recent works show that documents sanitized by PII removal techniques are vulnerable to reconstruction attacks. Yet, we suspect that the reported success of these attacks is largely overestimated. We critically analyze the evaluation of existing attacks and find that data leakage and data contamination are not properly mitigated, leaving the question whether or not PII removal techniques truly protect privacy in real-world scenarios unaddressed. We investigate possible data sources and attack setups that avoid data leakage and conclude that only truly private data can allow us to objectively evaluate vulnerabilities in PII removal techniques. However, access to private data is heavily restricted - and for good reasons - which also means that the public research community cannot address this problem in a transparent, reproducible, and trustworthy manner.