Detecting Face Synthesis Using a Concealed Fusion Model
This addresses security concerns related to fake biometrics in computer security, representing an incremental improvement over existing concealing solutions.
The paper tackled the problem of detecting synthesized face images by proposing a fusion-based strategy that conceals a new feature space using random polynomial coefficients and exponents, achieving state-of-the-art performance with protection against multiple attacks.
Face image synthesis is gaining more attention in computer security due to concerns about its potential negative impacts, including those related to fake biometrics. Hence, building models that can detect the synthesized face images is an important challenge to tackle. In this paper, we propose a fusion-based strategy to detect face image synthesis while providing resiliency to several attacks. The proposed strategy uses a late fusion of the outputs computed by several undisclosed models by relying on random polynomial coefficients and exponents to conceal a new feature space. Unlike existing concealing solutions, our strategy requires no quantization, which helps to preserve the feature space. Our experiments reveal that our strategy achieves state-of-the-art performance while providing protection against poisoning, perturbation, backdoor, and reverse model attacks.