Anonymization of Documents for Law Enforcement with Machine Learning

TL;DR

This paper introduces a machine learning system for automatically anonymizing scanned documents in law enforcement, reducing manual effort while ensuring compliance and maintaining forensic utility.

Contribution

It presents a novel self-supervised approach that requires only one example to anonymize all similar documents, outperforming existing automatic and naive methods.

Findings

Outperforms purely automatic redaction systems

Requires only one reference example for multiple documents

Reduces processing time significantly

Abstract

The steadily increasing utilization of data-driven methods and approaches in areas that handle sensitive personal information such as in law enforcement mandates an ever increasing effort in these institutions to comply with data protection guidelines. In this work, we present a system for automatically anonymizing images of scanned documents, reducing manual effort while ensuring data protection compliance. Our method considers the viability of further forensic processing after anonymization by minimizing automatically redacted areas by combining automatic detection of sensitive regions with knowledge from a manually anonymized reference document. Using a self-supervised image model for instance retrieval of the reference document, our approach requires only one anonymized example to efficiently redact all documents of the same type, significantly reducing processing time. We show that our approach outperforms both a purely automatic redaction system and also a naive copy-paste scheme of the reference anonymization to other documents on a hand-crafted dataset of ground truth redactions.