ML Security PapersSeeing Through the Blur: Unlocking Defocus Maps for Deepfake Detection
Published on arXiv
2509.23289
Output Integrity Attack
OWASP ML Top 10 — ML09
Key Finding
Defocus blur maps provide a reliable and physically interpretable forensic cue for identifying synthetic images across both facial deepfake and fully AI-generated scene scenarios.
Defocus Blur Map Detection
Novel technique introduced
The rapid advancement of generative AI has enabled the mass production of photorealistic synthetic images, blurring the boundary between authentic and fabricated visual content. This challenge is particularly evident in deepfake scenarios involving facial manipulation, but also extends to broader AI-generated content (AIGC) cases involving fully synthesized scenes. As such content becomes increasingly difficult to distinguish from reality, the integrity of visual media is under threat. To address this issue, we propose a physically interpretable deepfake detection framework and demonstrate that defocus blur can serve as an effective forensic signal. Defocus blur is a depth-dependent optical phenomenon that naturally occurs in camera-captured images due to lens focus and scene geometry. In contrast, synthetic images often lack realistic depth-of-field (DoF) characteristics. To capture these discrepancies, we construct a defocus blur map and use it as a discriminative feature for detecting manipulated content. Unlike RGB textures or frequency-domain signals, defocus blur arises universally from optical imaging principles and encodes physical scene structure. This makes it a robust and generalizable forensic cue. Our approach is supported by three in-depth feature analyses, and experimental results confirm that defocus blur provides a reliable and interpretable cue for identifying synthetic images. We aim for our defocus-based detection pipeline and interpretability tools to contribute meaningfully to ongoing research in media forensics. The implementation is publicly available at: https://github.com/irissun9602/Defocus-Deepfake-Detection
Key Contributions
- Physically interpretable deepfake detection framework using defocus blur maps — a depth-dependent optical cue that real camera-captured images possess but synthetic images typically lack
- Three in-depth feature analyses validating defocus blur as a generalizable and robust forensic signal beyond RGB textures or frequency-domain features
- Publicly available detection pipeline with interpretability tools for media forensics research
🛡️ Threat Analysis
Directly proposes a novel AI-generated content detection framework targeting deepfakes and AIGC images — defocus blur maps serve as the forensic/discriminative signal for output integrity verification. This is a novel detection architecture/technique, not a domain application of existing methods.