Worst-Case Morphs: a Theoretical and a Practical Approach
This work addresses security risks in biometric systems by providing insights into FR vulnerabilities, though it is incremental as it builds on existing morphing attack research.
The authors tackled the vulnerability of Face Recognition (FR) systems to morphing attacks by constructing worst-case morphs in the embedding space, showing that these can approximate a theoretical upper bound and fool unseen FR systems, with results demonstrating successful attacks.
Face Recognition (FR) systems have been shown to be vulnerable to morphing attacks. We examine exactly how challenging morphs can become. By showing a worst-case construction in the embedding space of an FR system and using a mapping from embedding space back to image space we generate images that show that this theoretical upper bound can be approximated if the FR system is known. The resulting morphs can also succesfully fool unseen FR systems and are useful for exploring and understanding the weaknesses of FR systems. Our method contributes to gaining more insight into the vulnerability of FR systems.