When used maliciously, deepfake can pose detrimental implications to political and social
forces including reducing public trust in institutions, damaging the reputation of prominent …

Synthetic realities are digital creations or augmentations that are contextually generated
through the use of Artificial Intelligence (AI) methods, leveraging extensive amounts of data …

In this paper, we consider the face swap** detection from the perspective of face identity.
Face swap** aims to replace the target face with the source face and generate the fake …

In this paper, we present novel synthetic training data called self-blended images (SBIs) to
detect deepfakes. SBIs are generated by blending pseudo source and target images from …

Deepfake detection remains a challenging task due to the difficulty of generalizing to new
types of forgeries. This problem primarily stems from the overfitting of existing detection …

Abstract Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of
machine learning systems. For instance, in autonomous driving, we would like the driving …

Existing face forgery detectors mainly focus on specific forgery patterns like noise
characteristics, local textures, or frequency statistics for forgery detection. This causes …

In this paper, we analyse the generalization ability of binary classifiers for the task of
deepfake detection. We find that the stumbling block to their generalization is caused by the …

With the springing up of face synthesis techniques, it is prominent in need to develop
powerful face forgery detection methods due to security concerns. Some existing methods …

Recent studies in deepfake detection have yielded promising results when the training and
testing face forgeries are from the same dataset. However, the problem remains challenging …