We describe the Forensics Adapter, an adapter network designed to transform CLIP into an effective and generalizable face forgery detector. Although CLIP is highly versatile, adapting it for face forgery detection is nontrivial as forgery-related knowledge is entangled with a wide range of unrelated knowledge. Existing methods treat CLIP merely as a feature extractor, lacking task-specific adaptation, which limits their effectiveness. To address this, we introduce an adapter to learn face forgery traces – the blending boundaries unique to forged faces, guided by task-specific objectives. Then we enhance the CLIP visual tokens with a dedicated interaction strategy that communicates knowledge across CLIP and the adapter. Since the adapter is alongside CLIP, its versatility is highly retained, naturally ensuring strong generalizability in face forgery detection. With only 5.7M trainable parameters, our method achieves a significant performance boost, improving by approximately 7% on average across five standard datasets. We believe the proposed method can serve as a baseline for future CLIP-based face forgery detection methods. The code is available at https://github.com/OUCVAS/ForensicsAdapter.

Image manipulation detection is to identify the authenticity of each pixel in images. One typical approach to uncover manipulation traces is to model image correlations. The previous methods commonly adopt the grids, which are fixed-size squares, as graph nodes to model correlations. However, these grids, being independent of image content, struggle to retain local content coherence, resulting in imprecise detection. To address this issue, we describe a new method named Hierarchical Region-aware Graph Reasoning (HRGR) to enhance image manipulation detection. Unlike existing grid-based methods, we model image correlations based on content-coherence feature regions with irregular shapes, generated by a novel Differentiable Feature Partition strategy. Then we construct a Hierarchical Region-aware Graph based on these regions within and across different feature layers. Subsequently, we describe a structural-agnostic graph reasoning strategy tailored for our graph to enhance the representation of nodes. Our method is fully differentiable and can seamlessly integrate into mainstream networks in an end-to-end manner, without requiring additional supervision. Extensive experiments demonstrate the effectiveness of our method in image manipulation detection, exhibiting its great potential as a plug-and-play component for existing architectures. Codes and models are available at https://github.com/OUC-VAS/HRGR-IMD.

Sequential DeepFake detection is an emerging task that predicts the manipulation sequence in order. Existing methods typically formulate it as an image-to-sequence problem, employing conventional Transformer architectures. However, these methods lack dedicated design and consequently result in limited performance. As such, this paper describes a new Transformer design, called TSOM, by exploring three perspectives: Texture, Shape, and Order of Manipulations. Our method features four major improvements: we describe a new texture-aware branch that effectively captures subtle manipulation traces with a Diversiform Pixel Difference Attention module. Then we introduce a Multi-source Cross-attention module to seek deep correlations among spatial and sequential features, enabling effective modeling of complex manipulation traces. To further enhance the cross-attention, we describe a Shape-guided Gaussian mapping strategy, providing initial priors of the manipulation shape. Finally, observing that the subsequent manipulation in a sequence may influence traces left in the preceding one, we intriguingly invert the prediction order from forward to backward, leading to notable gains as expected. Extensive experimental results demonstrate that our method outperforms others by a large margin, highlighting the superiority of our method.

Face-swapping DeepFakes have become an escalating societal concern, attracting increasing attention in recent years. To counter this, we investigate a new proactive defense framework to prevent individuals from being victimized in DeepFake videos. The core idea of this framework is to contaminate the inputs of DeepFake models by disrupting face detectors, based on the observation that face detectors are commonly used to automatically extract victim faces in most DeepFake techniques. Once the face detectors malfunction, the faces will not be correctly extracted, thereby impairing the training or synthesis stages of DeepFake models. To achieve this, we describe a strategy named FacePoison, which fools face detectors by adding dedicated adversarial perturbations to video frames. Building upon this, we introduce VideoFacePoison, an extended strategy that can efficiently propagate FacePoison across video frames instead of applying it individually to each frame, thus significantly reducing the computational overhead while retaining favorable attack performance. This framework is validated on five face detectors, and extensive experiments against eleven different DeepFake models demonstrate the effectiveness of disrupting face detectors to hinder DeepFake generation. The source code is publicly available at: https://github.com/OUC-VAS/FacePoison.

Quadrilateral mesh generation plays a crucial role in numerical simulations within Computer-Aided Design and Engineering (CAD/E). Producing high-quality quadrangulation typically requires satisfying four key criteria. First, the quadrilateral mesh should closely align with principal curvature directions. Second, singular points should be strategically placed and effectively minimized. Third, the mesh should accurately conform to sharp feature edges. Lastly, quadrangulation results should exhibit robustness against noise and minor geometric variations. Existing methods generally involve first computing a regular cross field to represent quad element orientations across the surface, followed by extracting a quadrilateral mesh aligned closely with this cross field. A primary challenge with this approach is balancing the smoothness of the cross field with its alignment to pre-computed principal curvature directions, which are sensitive to small surface perturbations and often ill-defined in spherical or planar regions. To tackle this challenge, we propose NeurCross , a novel framework that simultaneously optimizes a cross field and a neural signed distance function (SDF), whose zero-level set serves as a proxy of the input shape. Our joint optimization is guided by three factors: faithful approximation of the optimized SDF surface to the input surface, alignment between the cross field and the principal curvature field derived from the SDF surface, and smoothness of the cross field. Acting as an intermediary, the neural SDF contributes in two essential ways. First, it provides an alternative, optimizable base surface exhibiting more regular principal curvature directions for guiding the cross field. Second, we leverage the Hessian matrix of the neural SDF to implicitly enforce cross field alignment with principal curvature directions, thus eliminating the need for explicit curvature extraction. Extensive experiments demonstrate that NeurCross outperforms the state-of-the-art methods in terms of singular point placement, robustness against surface noise and surface undulations, and alignment with principal curvature directions and sharp feature curves.

Generating synthetic fake faces, known as pseudo-fake faces, is an effective way to improve the generalization of DeepFake detection. Existing methods typically generate these faces by blending real or fake faces in spatial domain. While these methods have shown promise, they overlook the simulation of frequency distribution in pseudo-fake faces, limiting the learning of generic forgery traces in-depth. To address this, this paper introduces {\em FreqBlender}, a new method that can generate pseudo-fake faces by blending frequency knowledge. Concretely, we investigate the major frequency components and propose a Frequency Parsing Network to adaptively partition frequency components related to forgery traces. Then we blend this frequency knowledge from fake faces into real faces to generate pseudo-fake faces. Since there is no ground truth for frequency components, we describe a dedicated training strategy by leveraging the inner correlations among different frequency knowledge to instruct the learning process. Experimental results demonstrate the effectiveness of our method in enhancing DeepFake detection, making it a potential plug-and-play strategy for other methods.

The prominent progress in generative models has significantly improved the authenticity of generated faces, raising serious concerns in society. To combat GAN-generated faces, many countermeasures based on Convolutional Neural Networks (CNNs) have been spawned due to their strong learning capabilities. In this paper, we rethink this problem and explore a new approach based on forest models instead of CNNs. Concretely, we describe a simple and effective forest-based method set, termed ForensicsForest Family, to detect GAN-generate faces. The ForensicsForest family is composed of three variants: ForensicsForest, Hybrid ForensicsForest and Divide-and-Conquer ForensicsForest. ForenscisForest is a novel Multi-scale Hierarchical Cascade Forest that takes appearance, frequency, and biological features as input, hierarchically cascades different levels of features for authenticity prediction, and employs a multi-scale ensemble scheme to consider different levels of information comprehensively for further performance improvement. Building upon ForensicsForest, we create Hybrid ForensicsForest, an extended version that integrates the CNN layers into models, to further enhance the efficacy of augmented features. Furthermore, to reduce memory usage during training, we introduce Divide-and-Conquer ForensicsForest, which can construct a forest model using only a portion of training samplings. In the training stage, we train several candidate forest models using the subsets of training samples. Then, a ForensicsForest is assembled by selecting suitable components from these candidate forest models. Our method is validated on state-of-the-art GAN-generated face datasets and compared with several CNN models, demonstrating the surprising effectiveness of our method in detecting GAN-generated faces.

Recent years have seen fast development in synthesizing realistic human faces using AI-based forgery technique called DeepFake, which can be weaponized to cause negative personal and social impacts. In this work, we develop a defense method, namely FacePosion, to prevent individuals from becoming victims of DeepFake videos by sabotaging would-be training data. This is achieved by disrupting face detection, a prerequisite step to prepare victim faces for training DeepFake model. Once the training faces are wrongly extracted, the DeepFake model can not be well trained. Specifically, we propose a multi-scale feature-level adversarial attack to disrupt the intermediate features of face detectors using different scales. Extensive experiments are conducted on seven various DeepFake models using six face detection methods, empirically showing that disrupting face detectors using our method can effectively obstruct DeepFakes.

We describe a simple and effective method called ForensicsForest to detect GAN-generate faces. Instead of using the commonly used CNN models, we describe a novel multi-scale hierarchical cascade forest, which takes semantic and frequency features as input, and hierarchically cascades different levels of features for authenticity prediction. We then propose a multi-scale ensemble, which comprehensively considers different levels of information to improve the performance further. Our method is validated on state-of-the-art GAN-generated face datasets in comparison with several CNN models, which demonstrates the surprising effectiveness of our method in detecting GAN-generated faces.

Abstract The problem of seamless parametrization of surfaces is of interest in the context of structured quadrilateral mesh generation and spline‐based surface approximation. It has been tackled by a variety of approaches, commonly relying on continuous numerical optimization to ultimately obtain suitable parameter domains. We present a general combinatorial seamless parameter domain construction, free from the potential numerical issues inherent to continuous optimization techniques in practice. The domains are constructed as abstract polygonal complexes which can be embedded in a discrete planar grid space, as unions of unit squares. We ensure that the domain structure matches any prescribed parametrization singularities (cones) and satisfies seamlessness conditions. Surfaces of arbitrary genus are supported. Once a domain suitable for a given surface is constructed, a seamless and locally injective parametrization over this domain can be obtained using existing planar disk mapping techniques, making recourse to Tutte's classical embedding theorem.

Seamless global parametrization of surfaces is a key operation in geometry processing, e.g., for high-quality quad mesh generation. A common approach is to prescribe the parametric domain structure, in particular, the locations of parametrization singularities (cones), and solve a non-convex optimization problem minimizing a distortion measure, with local injectivity imposed through either constraints or barrier terms. In both cases, an initial valid parametrization is essential to serve as a feasible starting point for obtaining an optimized solution. While convexified versions of the constraints eliminate this initialization requirement, they narrow the range of solutions, causing some problem instances that actually do have a solution to become infeasible. We demonstrate that for arbitrary given sets of topologically admissible parametric cones with prescribed curvature, a global seamless parametrization always exists (with the exception of one well-known case). Importantly, our proof is constructive and directly leads to a general algorithm for computing such parametrizations. Most distinctively, this algorithm is bootstrapped with a convex optimization problem (solving for a conformal map), in tandem with a simple linear equation system (determining a seamless modification of this map). This initial map can then serve as a valid starting point and be optimized for low distortion using existing injectivity preserving methods.