Robustness Analysis of Face Obscuration
This work addresses the need for systematic performance measurement in face obscuration to ensure privacy for law enforcement and media, though it is incremental as it applies existing evaluation methods to new techniques.
The paper tackled the problem of measuring the effectiveness of face obscuration techniques by evaluating eight methods across identification, verification, and reconstruction attacks, finding that k-same based methods were the most effective.
Face obscuration is needed by law enforcement and mass media outlets to guarantee privacy. Sharing sensitive content where obscuration or redaction techniques have failed to completely remove all identifiable traces can lead to many legal and social issues. Hence, we need to be able to systematically measure the face obscuration performance of a given technique. In this paper we propose to measure the effectiveness of eight obscuration techniques. We do so by attacking the redacted faces in three scenarios: obscured face identification, verification, and reconstruction. Threat modeling is also considered to provide a vulnerability analysis for each studied obscuration technique. Based on our evaluation, we show that the k-same based methods are the most effective.