Evaluating the Impact of Data Anonymization on Image Retrieval

2026-02-23

AI Summary

This study addresses the underexplored trade-off between privacy-preserving data anonymization and the performance of content-based image retrieval (CBIR). To systematically quantify the impact of anonymization on CBIR consistency, the authors propose an evaluation framework contextualized within DOKIQ, a real-world AI system used in law enforcement. Leveraging a DINOv2 self-distilled backbone, experiments are conducted across two public datasets and DOKIQ’s internal dataset, examining various anonymization methods, degrees of perturbation, and training strategies. The findings reveal that models trained on original, non-anonymized data maintain superior retrieval consistency even when querying anonymized images—a critical insight for designing CBIR systems that simultaneously satisfy privacy compliance requirements and retain high retrieval accuracy.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Privacy
• Data Mining & Knowledge Management: Intelligent Query Processing

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Security and Privacy: Data transparency and provenance

Abstract

With the growing importance of privacy regulations such as the General Data Protection Regulation, anonymizing visual data is becoming increasingly relevant across institutions. However, anonymization can negatively affect the performance of Computer Vision systems that rely on visual features, such as Content-Based Image Retrieval (CBIR). Despite this, the impact of anonymization on CBIR has not been systematically studied. This work addresses this gap, motivated by the DOKIQ project, an artificial intelligence-based system for document verification actively used by the State Criminal Police Office Baden-Württemberg. We propose a simple evaluation framework: retrieval results after anonymization should match those obtained before anonymization as closely as possible. To this end, we systematically assess the impact of anonymization using two public datasets and the internal DOKIQ dataset. Our experiments span three anonymization methods, four anonymization degrees, and four training strategies, all based on the state of the art backbone Self-Distillation with No Labels (DINO)v2. Our results reveal a pronounced retrieval bias in favor of models trained on original data, which produce the most similar retrievals after anonymization. The findings of this paper offer practical insights for developing privacy-compliant CBIR systems while preserving performance.

Problem

• data anonymization
• image retrieval
• privacy regulations
• computer vision
• CBIR

Innovation

• image anonymization
• content-based image retrieval
• DINOv2
• privacy-preserving computer vision
• evaluation framework