ML Security PapersDeep Data Hiding for ICAO-Compliant Face Images: A Survey
Jefferson David Rodriguez Chivata 1, Davide Ghiani 1, Simone Maurizio La Cava 1, Marco Micheletto 1, Giulia Orrù 1, Federico Lama 2, Gian Luca Marcialis 1
Published on arXiv
2508.19324
Output Integrity Attack
OWASP ML Top 10 — ML09
Key Finding
Identifies watermarking and steganography as viable post-capture complements to Presentation Attack Detection for countering deepfakes and morphing in ICAO biometric identity systems.
ICAO-compliant facial images, initially designed for secure biometric passports, are increasingly becoming central to identity verification in a wide range of application contexts, including border control, digital travel credentials, and financial services. While their standardization enables global interoperability, it also facilitates practices such as morphing and deepfakes, which can be exploited for harmful purposes like identity theft and illegal sharing of identity documents. Traditional countermeasures like Presentation Attack Detection (PAD) are limited to real-time capture and offer no post-capture protection. This survey paper investigates digital watermarking and steganography as complementary solutions that embed tamper-evident signals directly into the image, enabling persistent verification without compromising ICAO compliance. We provide the first comprehensive analysis of state-of-the-art techniques to evaluate the potential and drawbacks of the underlying approaches concerning the applications involving ICAO-compliant images and their suitability under standard constraints. We highlight key trade-offs, offering guidance for secure deployment in real-world identity systems.
Key Contributions
- First comprehensive survey of deep learning-based watermarking and steganography techniques specifically for ICAO-compliant facial images
- Evaluation of state-of-the-art data hiding approaches against ICAO standard constraints (imperceptibility, compression robustness, recognition preservation)
- Analysis of trade-offs and guidance for secure deployment in real-world identity systems (border control, digital travel credentials, KYC)
🛡️ Threat Analysis
The paper surveys content watermarking (embedding tamper-evident signals) and steganography for ICAO face images, specifically to authenticate content integrity and counter AI-generated threats including deepfakes and morphing attacks — core ML09 topics covering content provenance, watermarking, and AI-generated content detection.