Despite the promising results obtained by existing deepfake face detection methods for within-dataset detection, they often fail to generalize effectively to new datasets. We hypothesize that identity, a significant feature in facial recognition, is a key factor affecting deepfake detection models’ cross-dataset performance. In the feature space learned by a real/fake classifier, facial features may cluster based on identity rather than their authenticity, which undermines the classifier’s ability to distinguish between real and fake images. This paper introduces a novel training approach called Identity-Agnostic Learning (IAL) for deepfake face detection. IAL trains the detection model with identity-agnostic manner. It thus guides model to pay attention to the identity-irrelevant features. Experimental results demonstrate that our method effectively enhances the overall generalizability of deepfake face detection models.

Face morphing attacks circumvent face recognition systems (FRSs) by creating a morphed image that contains multiple identities. However, existing face morphing attack methods either sacrifice image quality or compromise the identity preservation capability. Consequently, these attacks fail to bypass FRSs verification well while still managing to deceive human observers. These methods typically rely on global information from contributing images, ignoring the detailed information from effective facial regions. To address the above issues, we propose a novel morphing attack method to improve the quality of morphed images and better preserve the contributing identities. Our proposed method leverages the hierarchical generative network to capture both local detailed and global consistency information. Additionally, a mask-guided image blending module is dedicated to removing artifacts from areas outside the face to improve the image's visual quality. The proposed attack method is compared to state-of-the-art methods on three public datasets in terms of FRSs' vulnerability, attack detectability, and image quality. The results show our method's potential threat of deceiving FRSs while being capable of passing multiple morphing attack detection (MAD) scenarios.

In this paper, we propose an innovative adversarial attack-based adaptive blending architecture (A3B) for face morphing attacks. Unlike traditional face morphing methods that evenly blend identity information using a half-half-hard strategy, we propose an approach that considers the varying importance of facial features in different regions of individuals for more precise and clear face morphing. Our method adaptively blends the latent codes of contributing subjects with a weighting mask that assigns different weights to different facial features when blending two faces to fuse their identities. The crux of our method lies in computing the weighting mask given a pair of contributing face images. This is done with the assistance of adversarial attacks, which can adaptively perturb face images to conceal or transfer identity. Owing to the adaptive blending strategy, our proposed approach achieves competitive performance on several state-of-the-art benchmark datasets. In contrast to existing methods, our approach explores the connection between adversarial attacks and morphing attacks for the first time, which generates morphed face images with plausible visual quality and simultaneously preserves the identity of contributing subjects. This novel perspective raises concerns about the potential security risks it poses to current facial recognition systems.

In this paper, we propose a novel approach for conducting face morphing attacks, which utilizes optimal-landmark-guided image blending. Current face morphing attack can be categorized into landmark-based and generation-based approaches. Landmark-based methods use geometric transformations to warp facial regions according to averaged landmarks, but often produce morphed images with poor visual quality. Generation-based methods, which employ generation models to blend multiple face images, can achieve better visual quality, but are often unsuccessful in generating morphed images that can effectively evade state-of-the-art face recognition systems (FRSs). Our proposed method overcomes the limitations of previous approaches by optimizing the morphing landmarks and using Graph Convolutional Networks (GCNs) to combine landmark and appearance features. We model facial landmarks as nodes in a bipartite graph that is fully connected, and utilize GCNs to simulate their spatial and structural relationships. The aim is to capture variations in facial shape and enable accurate manipulation of facial appearance features during the warping process, resulting in morphed facial images that are highly realistic and visually faithful. Experiments on two public datasets prove that our method inherits the advantages of previous landmark-based and generation-based methods and generates morphed images with higher quality, posing a more significant threat to state-of-the-art FRSs.

In this paper, we propose a Siamese graph learning (SGL) approach to alleviate aging dataset bias. While numerous semi-supervised algorithms have been successfully applied to classification tasks, most of them assume that both the labeled and unlabeled samples are drawn from identical distributions. However, this assumption may not hold due to the heterogeneity of face aging data, which gives rise to a bias and unpromising prediction. Motivated by this, our SGL learns to align the sparse distribution with the dense one for dataset debias with preserving the real aging smoothness. To achieve this, we adopt a mixup strategy to plausibly generate hallucinatory samples, which leverages amounts of unlabeled data to enhance the diversity of unbalanced classes. Moreover, we develop a graph contrastive regularization to suppress the noise introduced by auxiliary unlabeled samples. Extensive experimental results show compelling performance by only utilizing the limited scalability of training annotations.

In this paper, we propose a progressive margin loss (PML) approach for unconstrained facial age classification. Conventional methods make strong assumption on that each class owns adequate instances to outline its data distribution, likely leading to bias prediction where the training samples are sparse across age classes. Instead, our PML aims to adaptively refine the age label pattern by enforcing a couple of margins, which fully takes in the in-between discrepancy of the intra-class variance, inter-class variance and class center. Our PML typically incorporates with the ordinal margin and the variational margin, simultaneously plugging in the globally-tuned deep neural network paradigm. More specifically, the ordinal margin learns to exploit the correlated relationship of the real-world age labels. Accordingly, the variational margin is leveraged to minimize the influence of head classes that misleads the prediction of tailed samples. Moreover, our optimization carefully seeks a series of indicator curricula to achieve robust and efficient model training. Extensive experimental results on three face aging datasets demonstrate that our PML achieves compelling performance compared to state of the art. Code will be made publicly.

In this paper, we propose to learn a neighborhood-reasoning label distribution (NRLD) for facial age estimation. Unlike conventional label distribution methods with fixed-structural aging patterns, in this work, our NRLD aims to reason about more resilient and adaptive label distribution by disentangling the graph of face neighbors. In particular, our model holds the assumption on that the sample-specific age label distribution is principally influenced by a mixture of interpretable and meaningful factors, which typically cause plausible edges connected to the anchors. Under the scenario of each factor, we specifically collect the subset of graph edges and then convolute them with face samples to regress a mean-variance label distribution. During the training process, the mixture hyperparameters of our label distribution are iteratively optimized by following the Expectation-Maximization schema. Extensive experimental results on three challenging widely-evaluated datasets indicate the superiority in comparisons with most state of the arts.