Search

We report the observation of a pronounced third-order nonlinear Hall effect (NLHE) in 1$T$-phase VSe$_2$ nanosheets, synthesized using chemical vapor deposition (CVD). The nanosheets exhibit a charge density wave (CDW) transition at $\sim$77 K. Detailed angle-resolved and temperature-dependent measurements reveal a strong cubic relationship between the third-harmonic Hall voltage $V_{3\omega}^\perp$ and the bias current $I_\omega$, persisting up to room temperature. Notably, the third-order NLHE demonstrates a twofold angular dependence and significant enhancement below the CDW transition temperature, indicative of threefold symmetry breaking in the CDW phase. Scaling analysis suggests that the intrinsic contribution from the Berry connection polarizability tensor is substantially increased in the CDW phase, while extrinsic effects dominate at higher temperatures. Our findings highlight the critical role of CDW-induced symmetry breaking in modulating quantum geometric properties and nonlinear transport phenomena in VSe$_2$, paving the way for future explorations in low-dimensional quantum materials.

With the rapid advancement of generative models, the visual quality of generated images has become nearly indistinguishable from the real ones, posing challenges to content authenticity verification. Existing methods for detecting AI-generated images primarily focus on specific forgery clues, which are often tailored to particular generative models like GANs or diffusion models. These approaches struggle to generalize across architectures. Building on the observation that generative images often exhibit local anomalies, such as excessive smoothness, blurred textures, and unnatural pixel variations in small regions, we propose the localized discrepancy representation network (LDR-Net), a novel approach for detecting AI-generated images. LDR-Net captures smoothing artifacts and texture irregularities, which are common but often overlooked. It integrates two complementary modules: local gradient autocorrelation (LGA) which models local smoothing anomalies to detect smoothing anomalies, and local variation pattern (LVP) which captures unnatural regularities by modeling the complexity of image patterns. By merging LGA and LVP features, a comprehensive representation of localized discrepancies can be provided. Extensive experiments demonstrate that our LDR-Net achieves state-of-the-art performance in detecting generated images and exhibits satisfactory generalization across unseen generative models. The code will be released upon acceptance of this paper.

We report the observation of current-modulated magnetoresistance hysteresis below the superconducting transition temperature in the kagome superconductor CsV$_3$Sb$_5$. This highly tunable hysteresis behavior is confined to the superconducting state and vanishes when superconductivity is fully suppressed, directly linking magnetoresistance hysteresis to the superconducting order in CsV$_3$Sb$_5$. Additionally, the superconducting diode effect driven by a small magnetic field is observed, indicating the enhanced electronic magnetochiral anisotropy by the chiral domain-wall scattering. Our findings position CsV$_3$Sb$_5$ as a promising platform for exploring nontrivial physical phenomena, including unconventional pairing mechanisms and topological superconductivity.

The quantum geometric properties of topological materials underpin many exotic physical phenomena and applications. Quantum nonlinearity has emerged as a powerful probe for revealing these properties. The Berry curvature dipole in nonmagnetic materials and the quantum metric dipole in antiferromagnets have been explored by studying the second-order nonlinear Hall effect. Although the quadrupole moment of the quantum geometric tensor is theoretically predicted to induce higher-order quantum nonlinearity, the quantum metric quadrupole remains experimentally unexplored. Here, we report the quantum metric quadrupole induced third-order nonlinear longitudinal electrical response in few-layer WTe2, persisting up to room temperature. Angle-resolved third-harmonic current-voltage characteristics are found consistent with the intrinsic crystal symmetry of WTe2. Through temperature variation and scaling analysis, we identify the quantum metric quadrupole as the physical origin of the observed third-order longitudinal nonlinearity. Additionally, we determine the angle dependence of the quantum metric quadrupole, establishing third-order nonlinearity as an efficient method for revealing the quantum metric structure.

We establish sharp quantitative stability estimates near finite sums of ground states. The results depend on the dimension and the order of nonlinearity. In the complex valued case, the analysis becomes more intricate, depending on the phase difference.

We investigate the resistive anisotropy in CsV3Sb5 thin films within the charge density wave phase. Using a device structure with twelve electrodes symmetrically distributed in a circular shape, we measure the resistivity anisotropy by varying the current direction. A twofold resistivity anisotropy modulated by temperature is found, which is fully consistent with the electronic nematicity in CsV3Sb5, that is, the spontaneous rotational symmetry breaking by electronic degree of freedom. Additionally, the resistivity anisotropy also shows modest changes by applying magnetic fields, implying the possible chiral charge orders with time-reversal symmetry breaking. These findings provide deep insights into the correlated electronic states in Kagome materials and highlight the unique properties of CsV3Sb5 in the two-dimensional regime., Comment: 13 pages

Nonlinear transport plays a vital role in probing the quantum geometry of Bloch electrons, valley chirality, and carrier scattering mechanisms. The nonlinear Hall effect, characterized by a nonlinear scaling of Hall voltage with longitudinal current, has been explored to reveal the Berry curvature and quantum metric related physics. In this work, we extend the study of nonlinear transport to spin and valley degrees of freedom. Using bilayer graphene devices with Fe3GeTe2 contacts, we observe a second-order nonlinear spin current exhibiting spin valve-like behaviors. By tracking magnetic moment precession under an in-plane magnetic field, we identify a significantly enhanced critical magnetic field required for in-plane rotation, suggesting out-of-plane valley polarization induced by ferromagnetic proximity. These findings offer deep insights into the interplay of valley and spin in second-order nonlinear transport, opening avenues for promising device applications., Comment: 23 pages

We report on the observation of the linear anomalous Hall effect (AHE) in the nonmagnetic Weyl semimetal TaIrTe4. This is achieved by applying a direct current Idc and an alternating current Iac (Iac<

In this paper, we establish a Liouville theorem for solutions to the Lane Emden equation involving Baouendi Grushin operators. We focus on solutions that are stable outside a compact set. Specifically, we prove that when p is smaller than the Joseph Lundgren exponent and differs from the Sobolev exponent, 0 is the unique solution stable outside a compact set. This work extends the results obtained by Farina (J. Math. Pures Appl., 87 (5) (2007))., Comment: arXiv admin note: substantial text overlap with arXiv:2409.00646

Accurate dose distribution prediction is crucial in the radiotherapy planning. Although previous methods based on convolutional neural network have shown promising performance, they have the problem of over-smoothing, leading to prediction without important high-frequency details. Recently, diffusion model has achieved great success in computer vision, which excels in generating images with more high-frequency details, yet suffers from time-consuming and extensive computational resource consumption. To alleviate these problems, we propose Frequency-Decomposed Diffusion Model (FDDM) that refines the high-frequency subbands of the dose map. To be specific, we design a Coarse Dose Prediction Module (CDPM) to first predict a coarse dose map and then utilize discrete wavelet transform to decompose the coarse dose map into a low-frequency subband and three high-frequency subbands. There is a notable difference between the coarse predicted results and ground truth in high-frequency subbands. Therefore, we design a diffusion-based module called High-Frequency Refinement Module (HFRM) that performs diffusion operation in the high-frequency components of the dose map instead of the original dose map. Extensive experiments on an in-house dataset verify the effectiveness of our approach.

This paper establishes some Liouville type results for solutions to the Lane Emden equation on the entire Heisenberg group, both in the stable and stable outside a compact set scenarios.Specifically, we prove that when p is smaller than the Joseph Lundgren exponent and does not equal the Sobolev exponent, 0 is the unique solution that is stable outside a compact set., Comment: There is an error in equation 2.14. For equation 2.14 to hold, the function $u$ should be cylindrical

The Dynamic Communication Network (DCN) describes the interactions over time among various communication nodes, and it is widely used in Big-data applications as a data source. As the number of communication nodes increases and temporal slots accumulate, each node interacts in with only a few nodes in a given temporal slot, the DCN can be represented by an High-Dimensional Sparse (HDS) tensor. In order to extract rich behavioral patterns from an HDS tensor in DCN, this paper proposes an Adaptive Temporal-dependent Tensor low-rank representation (ATT) model. It adopts a three-fold approach: a) designing a temporal-dependent method to reconstruct temporal feature matrix, thereby precisely represent the data by capturing the temporal patterns; b) achieving hyper-parameters adaptation of the model via the Differential Evolutionary Algorithms (DEA) to avoid tedious hyper-parameters tuning; c) employing nonnegative learning schemes for the model parameters to effectively handle an the nonnegativity inherent in HDS data. The experimental results on four real-world DCNs demonstrate that the proposed ATT model significantly outperforms several state-of-the-art models in both prediction errors and convergence rounds., Comment: 10 pages, 2 figures

The rapid advancement of social media platforms has significantly reduced the cost of information dissemination, yet it has also led to a proliferation of fake news, posing a threat to societal trust and credibility. Most of fake news detection research focused on integrating text and image information to represent the consistency of multiple modes in news content, while paying less attention to inconsistent information. Besides, existing methods that leveraged inconsistent information often caused one mode overshadowing another, leading to ineffective use of inconsistent clue. To address these issues, we propose an adaptive multi-modal feature fusion network (MFF-Net). Inspired by human judgment processes for determining truth and falsity in news, MFF-Net focuses on inconsistent parts when news content is generally consistent and consistent parts when it is generally inconsistent. Specifically, MFF-Net extracts semantic and global features from images and texts respectively, and learns consistency information between modes through a multiple feature fusion module. To deal with the problem of modal information being easily masked, we design a single modal feature filtering strategy to capture inconsistent information from corresponding modes separately. Finally, similarity scores are calculated based on global features with adaptive adjustments made to achieve weighted fusion of consistent and inconsistent features. Extensive experimental results demonstrate that MFF-Net outperforms state-of-the-art methods across three public news datasets derived from real social medias.

In this paper, building on the ideas of Brasco and Pratelli (Geom. Funct. Anal., 22 (2012), 107-135), we establish a stability estimate for Bucur and Henrot's inequality (Acta Math., 222 (2019), 337-361). Their inequality asserts that, among regular sets of given measure, the disjoint union of two balls with the same radius maximizes the second non trivial eigenvalue of the Neumann Laplacian. Last week I was informed of the same result of this paper has been published by Wang K, Wu H. A quantitative Bucur Henrot inequality. Mathematische Nachrichten, 2022, 295(12): 2436-2451. So thearticle has been deprecated.

In this paper, we investigate the existence of weak solutions for a class of degenerate elliptic Dirichlet problems with critical nonlinearity and a logarithmic perturbation

The misuse of deepfake technology by malicious actors poses a potential threat to nations, societies, and individuals. However, existing methods for detecting deepfakes primarily focus on uncompressed videos, such as noise characteristics, local textures, or frequency statistics. When applied to compressed videos, these methods experience a decrease in detection performance and are less suitable for real-world scenarios. In this paper, we propose a deepfake video detection method based on 3D spatiotemporal trajectories. Specifically, we utilize a robust 3D model to construct spatiotemporal motion features, integrating feature details from both 2D and 3D frames to mitigate the influence of large head rotation angles or insufficient lighting within frames. Furthermore, we separate facial expressions from head movements and design a sequential analysis method based on phase space motion trajectories to explore the feature differences between genuine and fake faces in deepfake videos. We conduct extensive experiments to validate the performance of our proposed method on several compressed deepfake benchmarks. The robustness of the well-designed features is verified by calculating the consistent distribution of facial landmarks before and after video compression.Our method yields satisfactory results and showcases its potential for practical applications.

Existing image inpainting methods have achieved remarkable accomplishments in generating visually appealing results, often accompanied by a trend toward creating more intricate structural textures. However, while these models excel at creating more realistic image content, they often leave noticeable traces of tampering, posing a significant threat to security. In this work, we take the anti-forensic capabilities into consideration, firstly proposing an end-to-end training framework for anti-forensic image inpainting named SafePaint. Specifically, we innovatively formulated image inpainting as two major tasks: semantically plausible content completion and region-wise optimization. The former is similar to current inpainting methods that aim to restore the missing regions of corrupted images. The latter, through domain adaptation, endeavors to reconcile the discrepancies between the inpainted region and the unaltered area to achieve anti-forensic goals. Through comprehensive theoretical analysis, we validate the effectiveness of domain adaptation for anti-forensic performance. Furthermore, we meticulously crafted a region-wise separated attention (RWSA) module, which not only aligns with our objective of anti-forensics but also enhances the performance of the model. Extensive qualitative and quantitative evaluations show our approach achieves comparable results to existing image inpainting methods while offering anti-forensic capabilities not available in other methods.

AI-generated content has accelerated the topic of media synthesis, particularly Deepfake, which can manipulate our portraits for positive or malicious purposes. Before releasing these threatening face images, one promising forensics solution is the injection of robust watermarks to track their own provenance. However, we argue that current watermarking models, originally devised for genuine images, may harm the deployed Deepfake detectors when directly applied to forged images, since the watermarks are prone to overlap with the forgery signals used for detection. To bridge this gap, we thus propose AdvMark, on behalf of proactive forensics, to exploit the adversarial vulnerability of passive detectors for good. Specifically, AdvMark serves as a plug-and-play procedure for fine-tuning any robust watermarking into adversarial watermarking, to enhance the forensic detectability of watermarked images; meanwhile, the watermarks can still be extracted for provenance tracking. Extensive experiments demonstrate the effectiveness of the proposed AdvMark, leveraging robust watermarking to fool Deepfake detectors, which can help improve the accuracy of downstream Deepfake detection without tuning the in-the-wild detectors. We believe this work will shed some light on the harmless proactive forensics against Deepfake., Comment: Accepted by IJCAI 2024

Despite that deep learning methods have achieved remarkable performance in pathology image classification, they heavily rely on labeled data, demanding extensive human annotation efforts. In this study, we present a novel human annotation-free method for pathology image classification by leveraging pre-trained Vision-Language Models (VLMs). Without human annotation, pseudo labels of the training set are obtained by utilizing the zero-shot inference capabilities of VLM, which may contain a lot of noise due to the domain shift between the pre-training data and the target dataset. To address this issue, we introduce VLM-CPL, a novel approach based on consensus pseudo labels that integrates two noisy label filtering techniques with a semi-supervised learning strategy. Specifically, we first obtain prompt-based pseudo labels with uncertainty estimation by zero-shot inference with the VLM using multiple augmented views of an input. Then, by leveraging the feature representation ability of VLM, we obtain feature-based pseudo labels via sample clustering in the feature space. Prompt-feature consensus is introduced to select reliable samples based on the consensus between the two types of pseudo labels. By rejecting low-quality pseudo labels, we further propose High-confidence Cross Supervision (HCS) to learn from samples with reliable pseudo labels and the remaining unlabeled samples. Experimental results showed that our method obtained an accuracy of 87.1% and 95.1% on the HPH and LC25K datasets, respectively, and it largely outperformed existing zero-shot classification and noisy label learning methods. The code is available at https://github.com/lanfz2000/VLM-CPL., Comment: Under review

Each $x\in (0,1]$ can be uniquely expanded as a power-2-decaying Gauss-like expansion, in the form of \begin{equation*} x=\sum_{i=1}^{\infty}2^{-(d_1(x)+d_2(x)+\cdots+d_i(x))},\qquad d_i(x)\in \mathbb{N}. \end{equation*} Let $\phi:\mathbb{N}\to \mathbb{R}^{+}$ be an arbitrary positive function. We are interested in the size of the set $$F(\phi)=\{x\in (0,1]:d_n(x)\ge \phi(n)~~\text{for infinity many}~n\}.$$ We prove a Borel-Bernstein theorem on the zero-one law of the Lebesgue measure of $F(\phi)$. When the Lebesgue measure of $F(\phi)$ is zero, we calculate its Hausdorff dimension. Furthermore, we analyse the growth rate of the maximal digit among the first $n$ digits from probability and multifractal perspectives.

Deepfake videos are becoming increasingly realistic, showing few tampering traces on facial areasthat vary between frames. Consequently, existing Deepfake detection methods struggle to detect unknown domain Deepfake videos while accurately locating the tampered region. To address thislimitation, we propose Delocate, a novel Deepfake detection model that can both recognize andlocalize unknown domain Deepfake videos. Ourmethod consists of two stages named recoveringand localization. In the recovering stage, the modelrandomly masks regions of interest (ROIs) and reconstructs real faces without tampering traces, leading to a relatively good recovery effect for realfaces and a poor recovery effect for fake faces. Inthe localization stage, the output of the recoveryphase and the forgery ground truth mask serve assupervision to guide the forgery localization process. This process strategically emphasizes the recovery phase of fake faces with poor recovery, facilitating the localization of tampered regions. Ourextensive experiments on four widely used benchmark datasets demonstrate that Delocate not onlyexcels in localizing tampered areas but also enhances cross-domain detection performance., Comment: arXiv admin note: substantial text overlap with arXiv:2308.09921, arXiv:2305.05943

We reveal the gate-tunable Berry curvature dipole polarizability in Dirac semimetal Cd3As2 nanoplates through measurements of the third-order nonlinear Hall effect. Under an applied electric field, the Berry curvature exhibits an asymmetric distribution, forming a field-induced Berry curvature dipole, resulting in a measurable third-order Hall voltage with a cubic relationship to the longitudinal electric field. Notably, the magnitude and polarity of this third-order nonlinear Hall effect can be effectively modulated by gate voltages. Furthermore, our scaling relation analysis demonstrates that the sign of the Berry curvature dipole polarizability changes when tuning the Fermi level across the Dirac point, in agreement with theoretical calculations. The results highlight the gate control of nonlinear quantum transport in Dirac semimetals, paving the way for promising advancements in topological electronics.

In this paper, we study the semilinear subelliptic equation \[ \left\{ \begin{array}{cc} -\triangle_{X} u=f(x,u)+g(x,u) & \mbox{in}~\Omega, \\[2mm] u=0\hfill & \mbox{on}~\partial\Omega, \end{array} \right. \] where $\triangle_{X}=-\sum_{i=1}^{m}X_{i}^{*}X_{i}$ is the self-adjoint H\"{o}rmander operator associated with vector fields $X=(X_{1},X_{2},\ldots,X_{m})$ satisfying the H\"{o}rmander condition, $f(x,u)\in C(\overline{\Omega}\times \mathbb{R})$, $g(x,u)$ is a Carath\'{e}odory function on $\Omega\times \mathbb{R}$, and $\Omega$ is an open bounded domain in $\mathbb{R}^n$ with smooth boundary. Combining the perturbation from symmetry method with the approaches involving eigenvalue estimate and Morse index in estimating the min-max values, we obtain two kinds of existence results for multiple weak solutions to the problem above. Furthermore, we discuss the difference between the eigenvalue estimate approach and the Morse index approach in degenerate situations. Compared with the classical elliptic cases, both approaches here have their own strengths in the degenerate cases. This new phenomenon implies the results in general degenerate cases would be quite different from the situations in classical elliptic cases., Comment: 39 pages

The exploitation of Deepfake techniques for malicious intentions has driven significant research interest in Deepfake detection. Deepfake manipulations frequently introduce random tampered traces, leading to unpredictable outcomes in different facial regions. However, existing detection methods heavily rely on specific forgery indicators, and as the forgery mode improves, these traces become increasingly randomized, resulting in a decline in the detection performance of methods reliant on specific forgery traces. To address the limitation, we propose Recap, a novel Deepfake detection model that exposes unspecific facial part inconsistencies by recovering faces and enlarges the differences between real and fake by mapping recovered faces. In the recovering stage, the model focuses on randomly masking regions of interest (ROIs) and reconstructing real faces without unpredictable tampered traces, resulting in a relatively good recovery effect for real faces while a poor recovery effect for fake faces. In the mapping stage, the output of the recovery phase serves as supervision to guide the facial mapping process. This mapping process strategically emphasizes the mapping of fake faces with poor recovery, leading to a further deterioration in their representation, while enhancing and refining the mapping of real faces with good representation. As a result, this approach significantly amplifies the discrepancies between real and fake videos. Our extensive experiments on standard benchmarks demonstrate that Recap is effective in multiple scenarios., Comment: arXiv admin note: substantial text overlap with arXiv:2305.05943

Due to the progression of information technology in recent years, document images have been widely disseminated on social networks. With the help of powerful image editing tools, document images are easily forged without leaving visible manipulation traces, which leads to severe issues if significant information is falsified for malicious use. Therefore, the research of document image forensics is worth further exploring. In this paper, we propose a Character Texture Perception Network (CTP-Net) to localize the forged regions in document images. Specifically, considering the characters with semantics in a document image are highly vulnerable, capturing the forgery traces is the key to localize the forged regions. We design a Character Texture Stream (CTS) based on optical character recognition to capture features of text areas that are essential components of a document image. Meanwhile, texture features of the whole document image are exploited by an Image Texture Stream (ITS). Combining the features extracted from the CTS and the ITS, the CTP-Net can reveal more subtle forgery traces from document images. Moreover, to overcome the challenge caused by the lack of fake document images, we design a data generation strategy that is utilized to construct a Fake Chinese Trademark dataset (FCTM). Experimental results on different datasets demonstrate that the proposed CTP-Net is able to localize multi-scale forged areas in document images, and outperform the state-of-the-art forgery localization methods, even though post-processing operations are applied.

Segmentation of pathological images is a crucial step for accurate cancer diagnosis. However, acquiring dense annotations of such images for training is labor-intensive and time-consuming. To address this issue, Semi-Supervised Learning (SSL) has the potential for reducing the annotation cost, but it is challenged by a large number of unlabeled training images. In this paper, we propose a novel SSL method based on Cross Distillation of Multiple Attentions (CDMA) to effectively leverage unlabeled images. Firstly, we propose a Multi-attention Tri-branch Network (MTNet) that consists of an encoder and a three-branch decoder, with each branch using a different attention mechanism that calibrates features in different aspects to generate diverse outputs. Secondly, we introduce Cross Decoder Knowledge Distillation (CDKD) between the three decoder branches, allowing them to learn from each other's soft labels to mitigate the negative impact of incorrect pseudo labels in training. Additionally, uncertainty minimization is applied to the average prediction of the three branches, which further regularizes predictions on unlabeled images and encourages inter-branch consistency. Our proposed CDMA was compared with eight state-of-the-art SSL methods on the public DigestPath dataset, and the experimental results showed that our method outperforms the other approaches under different annotation ratios. The code is available at \href{https://github.com/HiLab-git/CDMA}{https://github.com/HiLab-git/CDMA.}, Comment: Provisional Accepted by MICCAI 2023

Unlike hiding bit-level messages, hiding image-level messages is more challenging, which requires large capacity, high imperceptibility, and high security. Although recent advances in hiding image-level messages have been remarkable, existing schemes are limited to lossless spatial images as covers and cannot be directly applied to JPEG images, the ubiquitous lossy format images in daily life. The difficulties of migration are caused by the lack of targeted design and the loss of details due to lossy decompression and re-compression. Considering that taking DCT densely on $8\times8$ image patches is the core of the JPEG compression standard, we design a novel model called \textsf{EFDR}, which can comprehensively \underline{E}xploit \underline{F}ine-grained \underline{D}CT \underline{R}epresentations and embed the secret image into quantized DCT coefficients to avoid the lossy process. Specifically, we transform the JPEG cover image and hidden secret image into fine-grained DCT representations that compact the frequency and are associated with the inter-block and intra-block correlations. Subsequently, the fine-grained DCT representations are further enhanced by a sub-band features enhancement module. Afterward, a transformer-based invertibility module is designed to fuse enhanced sub-band features. Such a design enables a fine-grained self-attention on each sub-band and captures long-range dependencies while maintaining excellent reversibility for hiding and recovery. To our best knowledge, this is the first attempt to embed a color image of equal size in a color JPEG image. Extensive experiments demonstrate the effectiveness of our \textsf{EFDR} with superior performance., Comment: ACM Multimedia 23 submitted by Xin Liao (https://xin-liao.github.io/)

Deepfake techniques have been widely used for malicious purposes, prompting extensive research interest in developing Deepfake detection methods. Deepfake manipulations typically involve tampering with facial parts, which can result in inconsistencies across different parts of the face. For instance, Deepfake techniques may change smiling lips to an upset lip, while the eyes remain smiling. Existing detection methods depend on specific indicators of forgery, which tend to disappear as the forgery patterns are improved. To address the limitation, we propose Mover, a new Deepfake detection model that exploits unspecific facial part inconsistencies, which are inevitable weaknesses of Deepfake videos. Mover randomly masks regions of interest (ROIs) and recovers faces to learn unspecific features, which makes it difficult for fake faces to be recovered, while real faces can be easily recovered. Specifically, given a real face image, we first pretrain a masked autoencoder to learn facial part consistency by dividing faces into three parts and randomly masking ROIs, which are then recovered based on the unmasked facial parts. Furthermore, to maximize the discrepancy between real and fake videos, we propose a novel model with dual networks that utilize the pretrained encoder and masked autoencoder, respectively. 1) The pretrained encoder is finetuned for capturing the encoding of inconsistent information in the given video. 2) The pretrained masked autoencoder is utilized for mapping faces and distinguishing real and fake videos. Our extensive experiments on standard benchmarks demonstrate that Mover is highly effective., Comment: arXiv admin note: substantial text overlap with arXiv:2303.01740

Malicious Deepfakes have led to a sharp conflict over distinguishing between genuine and forged faces. Although many countermeasures have been developed to detect Deepfakes ex-post, undoubtedly, passive forensics has not considered any preventive measures for the pristine face before foreseeable manipulations. To complete this forensics ecosystem, we thus put forward the proactive solution dubbed SepMark, which provides a unified framework for source tracing and Deepfake detection. SepMark originates from encoder-decoder-based deep watermarking but with two separable decoders. For the first time the deep separable watermarking, SepMark brings a new paradigm to the established study of deep watermarking, where a single encoder embeds one watermark elegantly, while two decoders can extract the watermark separately at different levels of robustness. The robust decoder termed Tracer that resists various distortions may have an overly high level of robustness, allowing the watermark to survive both before and after Deepfake. The semi-robust one termed Detector is selectively sensitive to malicious distortions, making the watermark disappear after Deepfake. Only SepMark comprising of Tracer and Detector can reliably trace the trusted source of the marked face and detect whether it has been altered since being marked; neither of the two alone can achieve this. Extensive experiments demonstrate the effectiveness of the proposed SepMark on typical Deepfakes, including face swapping, expression reenactment, and attribute editing., Comment: Accepted by ACM MM 2023

The mushroomed Deepfake synthetic materials circulated on the internet have raised a profound social impact on politicians, celebrities, and individuals worldwide. In this survey, we provide a thorough review of the existing Deepfake detection studies from the reliability perspective. We identify three reliability-oriented research challenges in the current Deepfake detection domain: transferability, interpretability, and robustness. Moreover, while solutions have been frequently addressed regarding the three challenges, the general reliability of a detection model has been barely considered, leading to the lack of reliable evidence in real-life usages and even for prosecutions on Deepfake-related cases in court. We, therefore, introduce a model reliability study metric using statistical random sampling knowledge and the publicly available benchmark datasets to review the reliability of the existing detection models on arbitrary Deepfake candidate suspects. Case studies are further executed to justify the real-life Deepfake cases including different groups of victims with the help of the reliably qualified detection models as reviewed in this survey. Reviews and experiments on the existing approaches provide informative discussions and future research directions for Deepfake detection., Comment: Accepted to ACM Computing Surveys