The proliferation of AI-generated imagery poses escalating challenges for multimedia forensics, yet many existing detectors depend on assumptions about the internals of specific generative models, limiting their cross-model applicability. We introduce a self-supervised approach for detecting AI-generated images that leverages camera metadata-specifically exchangeable image file format (EXIF) tags-to learn features intrinsic to digital photography. Our pretext task trains a feature extractor solely on camera-captured photographs by classifying categorical EXIF tags (e.g., camera model and scene type) and pairwise-ranking ordinal and continuous EXIF tags (e.g., focal length and aperture value). Using these EXIF-induced features, we first perform one-class detection by modeling the distribution of photographic images with a Gaussian mixture model and flagging low-likelihood samples as AI-generated. We then extend to binary detection that treats the learned extractor as a strong regularizer for a classifier of the same architecture, operating on high-frequency residuals from spatially scrambled patches. Extensive experiments across various generative models demonstrate that our EXIF-induced detectors substantially advance the state of the art, delivering strong generalization to in-the-wild samples and robustness to common benign image perturbations.

The detection of AI-generated faces is commonly approached as a binary classification task. Nevertheless, the resulting detectors frequently struggle to adapt to novel AI face generators, which evolve rapidly. In this paper, we describe an anomaly detection method for AI-generated faces by leveraging self-supervised learning of camera-intrinsic and face-specific features purely from photographic face images. The success of our method lies in designing a pretext task that trains a feature extractor to rank four ordinal exchangeable image file format (EXIF) tags and classify artificially manipulated face images. Subsequently, we model the learned feature distribution of photographic face images using a Gaussian mixture model. Faces with low likelihoods are flagged as AI-generated. Both quantitative and qualitative experiments validate the effectiveness of our method. Our code is available at https://github.com/MZMMSEC/AIGFD_EXIF.git.

In recent years, the multimedia forensics and security community has seen remarkable progress in multitask learning for DeepFake (i.e., face forgery) detection. The prevailing approach has been to frame DeepFake detection as a binary classification problem augmented by manipulation-oriented auxiliary tasks. This scheme focuses on learning features specific to face manipulations with limited generalizability. In this paper, we delve deeper into semantics-oriented multitask learning for DeepFake detection, capturing the relationships among face semantics via joint embedding. We first propose an automated dataset expansion technique that broadens current face forgery datasets to support semantics-oriented DeepFake detection tasks at both the global face attribute and local face region levels. Furthermore, we resort to the joint embedding of face images and labels (depicted by text descriptions) for prediction. This approach eliminates the need for manually setting task-agnostic and task-specific parameters, which is typically required when predicting multiple labels directly from images. In addition, we employ bi-level optimization to dynamically balance the fidelity loss weightings of various tasks, making the training process fully automated. Extensive experiments on six DeepFake datasets show that our method improves the generalizability of DeepFake detection and renders some degree of model interpretation by providing human-understandable explanations.

In recent years, deep learning has greatly streamlined the process of manipulating photographic face images. Aware of the potential dangers, researchers have developed various tools to spot these counterfeits. Yet, none asks the fundamental question:What digital manipulations make a real photographic face image fake, while others do not? In this paper, we put face forgery in a semantic context and define thatcomputational methods that alter semantic face attributes to exceed human discrimination thresholds are sources of face forgery. Following our definition, we construct a large face forgery image dataset, where each image is associated with a set of labels organized in a hierarchical graph. Our dataset enables two new testing protocols to probe the generalizability of face forgery detectors. Moreover, we propose a semantics-oriented face forgery detection method that captures label relations and prioritizes the primary task (i.e., real or fake face detection). We show that the proposed dataset successfully exposes the weaknesses of current detectors as the test set and consistently improves their generalizability as the training set. Additionally, we demonstrate the superiority of our semantics-oriented method over traditional binary and multi-class classification-based detectors.

Most computer vision algorithms require parameter adjustment according to the image noise level. Conventionally, the additive white Gaussian noise (AWGN) model is widely used in most noise estimation algorithms; however, this assumption does not hold in the real world where the noise from cameras is more complex, and it is more appropriate to assume the signal-dependent noise (SDN) model. In this paper, we focus on the SDN model while considering the nonlinear radiometric calibration inside an actual camera, and propose an algorithm to efficiently estimate the noise level function (NLF), which is defined as the noise standard deviation with respect to image intensity. First, the input image is divided into overlapping patches, and noise samples are estimated in the linear transform domain. The confidence levels of the noise samples and the prior of the camera response function are then employed as constraints for the recovery of the NLF. Finally, the noise samples and constraints are represented in a convex optimization problem. The experimental results using both real and synthetic noisy images demonstrate the superiority of the proposed method. In addition, the estimated NLFs are incorporated into two well-known denoising schemes, non-local means and BM3D, and shows significant improvements in denoising SDN-polluted images.

Noise is the most common type of image distortion affecting human visual perception. In this paper, we propose a no-reference image quality assessment (IQA) method for noisy images incorporating the features of entropy, gradient, and kurtosis. Specifically, image noise estimation is conducted in the discrete cosine transform domain based on skewness invariance. In the principal component analysis domain, kurtosis feature is obtained by statistically counting the significant differences between images with and without noise. In addition, both the consistency between the entropy and kurtosis features and the subjective scores are improved by combining them with the gradient coefficient. Support vector regression is applied to map all extracted features into an integrated scoring system. The proposed method is evaluated in three mainstream databases (i.e., LIVE, TID2013, and CSIQ), and the results demonstrate the superiority of the proposed method according to the Pearson linear correlation coefficient which is the most significant indicator in IQA.