The rapid advancement of facial manipulation technologies demands detection systems that can generalize to novel forgery techniques. We identify that Standard Learning, reliant on static datasets and uniform sampling, detrimentally biases models towards specific patterns tied to individual generation techniques, hindering their ability to learn general features. To overcome this, we introduce Adaptive Learning (AL) for face forgery detection, a cyclical framework that simultaneously refines both the detector model and the training data through dynamic sample selection and model optimization. AL’s efficacy hinges on identifying samples rich in generalizable forgery clues. Thus, we propose Augmentation Robustness Validation (ARV) as AL’s core purification engine. ARV exploits the stability of predictions across diverse semantic-preserving augmentations as a reliable proxy for general feature presence: samples that exhibit invariant predictions inherently contain robust manipulation traces. Integrating ARV with AL yields Adaptive Learning with Augmentation Robustness Validation (ALarv). ALarv strategically prioritizes stability-verified samples during iterative training cycles, progressively enhancing the model’s focus on transferable forensic features. Inspired by the architectural advantages of ConvNeXt, we incorporate it into ALarv, forming an effective method, ALarv-ConvNeXt. Extensive experiments demonstrate ALarv-ConvNeXt’s superior generalization performance, including emerging diffusion-based synthetic faces.

A prevalent video manipulation technique involves upsampling the bitrate parameter without modifying the underlying video content, often implemented under the pretext of improving viewer appeal and monetization potential. Such deceptive practices, which substitute fake bitrate specifications for genuine ones, mislead audiences and platforms while directly infringing copyright protections, constituting a form of manipulation that forensic experts classify as fake bitrate video manipulation. Addressing the issue of detecting fake bitrate Versatile Video Coding (VVC) videos, an algorithm based on hierarchical feature mapping in the coding domain is proposed. We first analyze the Coding Unit (CU) partitioning and the deblocking filtering of fake bitrate VVC videos during multiple encoding processes. Then, CU partitioning and deblocking decision-mode information in the coding domain are extracted during the decoding process. By combining the positional information, the CU Difference feature map (FCD) and the Deblocking Filtering Difference feature map (FDD) are obtained through a hierarchical mapping of the encoding feature, which are further enhanced by calculating the eccentric covariance matrix. After that, the enhanced feature maps are fed into a Dual-branch Difference Perception (DDP) module to obtain frame-level detection results. By comparing with existing algorithms, the experimental results demonstrate that the proposed algorithm achieves superior detection accuracy in different scenarios, validating its effectiveness and robustness.

As image-generative AI models become increasingly accessible to the public, the demand for content safety has surged. Although model developers have introduced alignment mechanisms to prevent the creation of threatening images, and extensive researches have been conducted on verifying the authenticity of AI-generated images, a significant number of ex-regulatory images have been discovered that fall into regulatory gaps. These images are neither covered by existing alignment mechanisms nor included in the scope of current detection methods. To address this, we introduce ExDA, a detection and attribution framework specifically designed for such ex-regulatory images. ExDA utilizes a frozen CLIP:ViT-L/14 as a visual feature extractor to extract rich and unbiased visual features, complemented by a text feature reduction layer to unify semantic styles. For obtaining highly discriminative features, ExDA introduces an SFS-ResNet network, where each basic layer is replaced with a meticulously designed Multi-Channel Margin Convolution (MMConv). Additionally, a plug-and-play multi-generation model attributor is integrated behind the detector. Given the lack of ex-regulatory images in existing public datasets, we constructed ExImage, a dataset containing 72,000 ex-regulatory images, to validate ExDA's effectiveness. Experiments show that ExDA achieves an average detection accuracy of 99.07% on ExImage, and demonstrating significant performance improvements of +5.73% and +10.36% on GenImage and high-challenge Chameleon datasets respectively in cross-datasets evaluation. Notably, ExDA also achieves excellent performance in attribution tasks, demonstrating its superior ability to identify the intrinsic fingerprints of generative models. Our code is available at https://github.com/mwp-create-wonders/ExDA.

The rapid advancement of AI-driven multimedia manipulation has created an urgent need for more sophisticated digital forensics solutions. Current detection methods, while effective against specific tampering types, suffer from limited generalizability across diverse manipulation techniques. To address this challenge, researchers have developed Double Compression Detection (DCD) as a universal approach through compression-domain analysis. This review presents the comprehensive analysis of DCD techniques, systematically evaluating cutting-edge techniques for audio, image, and video content forensics. The pros and cons of existing DCD schemes are summarized for the first time from the perspective of generalization and effectiveness in this review. The emerging trends and fundamental limitations of existing researches are critically examined to guide future research directions in DCD.

Compared with traditional modification image steganography, coverless image steganography can resist the detection of steganalysis algorithms relying on no modification to the carriers. Previous works have made great efforts to improve the robustness against image attacks. However, the robustness of resisting geometric attacks performs not that well. After studying the general flow of the coverless image steganography, we find out that the receiver always needs to generate or map the hash sequences directly from the received images, which causes a significantly negative impact for extracting correct secret information because these received images might be attacked. Inspired by this finding, we surprisingly explore a common way to solve the problem by proposing a universal restoration framework for the attacked images. The most important module of the framework, the restoration module, contains two main parts, i.e., the classification sub-module and the attack restoration sub-module. The attacked images at the receiving end are first sent to a classification sub-module to estimate the type of the attack. Then, the corresponding attack restoration sub-module is utilized to repair the attacked images to improve the robustness. Experimental results show that the robustness of the existing coverless image steganography methods have been greatly improved after using the proposed framework without introducing extra security issues.

The growing adoption of 3D point cloud in applications like autonomous driving has heightened concerns about their vulnerability to adversarial attacks. Existing defense methods face two fundamental challenges: ineffective detection of imperceptible adversarial examples and poor restoration of severely distorted point cloud. In this paper, we present ADDR, an end-to-end defense framework that integratesBinary Geometric Feature Anomaly Detection (BGFAD)andDistorted point cloud Restoration (DPCR). BGFAD employs a dual threshold mechanism combining global distance statistics and local curvature analysis to detect both substantial and imperceptible adversarial perturbations. DPCR leverages attention enhanced feature encoding to reconstruct missing geometric structures while preserving semantic integrity through bidirectional Chamfer loss optimization. Our framework uniquely bridges traditional geometric priors with deep learning mechanisms, achieving attack-agnostic defense without classifier retraining. Extensive experiments on ModelNet40, ShapeNet and ScanObjectNN datasets demonstrate state-of-the-art performance, with about 12% higher robustness against structural attacks and 6× better restoration fidelity than existing methods. ADDR maintains real-time processing capabilities while reducing adversarial success rates to <5% across diverse attacks. The code is available at https://github.com/whwh456/ADDR.

Compared with traditional video steganography, coverless video steganography (CVS) can completely avoid being detected by steganalysis algorithms. Recently, the study of CVS has developed rapidly. However, it is still far from the theoretical maximum values in capacity, i.e., the theoretical limit is$2^\ell$for a hash sequence length of$\ell$. Besides, most existing CVS methods have only considered limited types of video attacks in robustness. In this paper, a novel coverless video steganography based on two-level discrete cosine transform (DCT) features is proposed. First, pre-processing is accomplished on the public video datasets. Then, two-level DCT features are calculated and the Coverless Video Database (CVD) is constructed by the K-means++ clustering algorithm. After that, the mapping table is established to map the secret segments to the CVD. Finally, each secret segment corresponds to a video sequence in the CVD by the mapping table to complete the process of information embedding and extraction. The proposed method first evaluates the robustness against the frame swapping attack, which is a common video attack. Experimental results show that the proposed method can achieve the theoretical maximum value in effective capacity and better robustness compared to the state-of-the-art works.

In the previous efforts to counteract Deepfake, detection methods were most adopted, but they could only function after-effect and could not undo the harm. Preemptive defense has recently gained attention as an alternative, but such defense works have either limited their scenario to facial-reenactment Deepfake models or only targeted specific face-swapping Deepfake model. Motivated to fill this gap, we start by establishing the Deepfake scenario modeling and finding the scenario difference among categories, then move on to the face-swapping scenario setting overlooked by previous works. Based on this scenario, we first propose a novel Black-Box Penetrating Defense Process that enables defense against face-swapping models without prior model knowledge. Then we propose a novel Double-Blind Feedback Regulation Strategy to solve the reality problem of avoiding alarming distortions after defense that had previously been ignored, which helps conduct valid preemptive defense against face-swapping Deepfake models in reality. Experimental results in comparison with state-of-the-art defense methods are conducted against popular face-swapping Deepfake models, proving our proposed method valid under practical circumstances.

In the field of HEVC (High Efficiency Video Coding) double compression detection, relocated I-frame (RI frame) detection and original GOP size estimation are two significant problems for video forensics. However, little research explores the interconnection between the two problems, and effective methods to resolve them are still lacking. In this paper, a novel feature model called In-loop Filtering and CU Depth Map (IFCDM) is proposed to accurately detect RI frames, and the intrinsic correlation between RI frames and GOP structure is explored, which can be used for original GOP size estimation. Theoretical and statistical analysis of HEVC recompression process is first carried out. Then, sub-features of HEVC in-loop filtering modes and CU partition depth are extracted, and transformed into grey-scale maps to construct IFCDM. A neural network, consisting of tiny Vision Transformer and LSTM, is trained to learn spatial and temporal representations of input features, and further derive the RI frame detection results. Finally, an adaptive periodic analysis algorithm is designed, to integrate the RI frame detection results and estimate the original GOP size of recompressed videos. Experiments show that our method can outperform the existing state-of-the-art methods in both frame level and video level.

Abstract Detection of computer-generated (CG) images can reveal the authenticity and originality of digital images. However, recent cutting-edge image generation methods make it very difficult to distinguish CG images from natural photographs. In this paper, a novel method based on color patterns and enhanced texture learning is proposed to tackle this problem. We designed and implemented the backbone network with a separation-fusion learning strategy by constructing a multi-branch neural network. The luminance and chrominance patterns in dual-color spaces (RGB and YCbCr) are leveraged to achieve a robust representation of image differences. A channel-spatial attention module and a global texture enhancement module are also integrated into a backbone network to enhance the learning of inherent traces. Experiments on several commonly used benchmark datasets and a newly constructed dataset with more realistic and diverse images demonstrate that the proposed algorithm outperforms state-of-the-art competitors by a large margin.

Federated learning (FL) can complete collaborative model training without transferring local data, which can greatly improve the training efficiency. However, FL is susceptible data and model backdoor attacks. To address data backdoor attack, in this article, we propose a defense method named TSF. TSF transforms data from time domain to frequency domain and subsequently designs a low-pass filter to mitigate the impact of high-frequency signals introduced by backdoor samples. Additionally, we undergo homomorphic encryption on local updates to prevent the server from inferring user’s data. We also introduce a defense method against model backdoor attack named ciphertext field similarity detect differential privacy (CFSD-DP). CFSD-DP screens malicious updates using cosine similarity detection in the ciphertext domain. It perturbs the global model using differential privacy mechanism to mitigate the impact of model backdoor attack. It can effectively detect malicious updates and safeguard the privacy of the global model. Experimental results show that the proposed TSF and CFSD-DP have 73.8% degradation in backdoor accuracy while only 3% impact on the main task accuracy compared with state-of-the-art schemes. Code is available athttps://github.com/whwh456/TSF.

With a deeper understanding of the security issues in steganography, coverless steganography has become a hotspot due to no modification to the carriers. However, the existing coverless video steganographic algorithms have considered a few types of video attacks. In this paper, a robust coverless video steganography based on the similarity of inter-frames is proposed. First, a public video database is selected and preprocessed to construct a Secret Communication Video Database (SCVD). The similarity score between the first and last frames is calculated for video sorting to utilize the temporal characteristics of videos. After that, the mapping table between the secret information and the SCVD is designed for both senders and receivers. Finally, each secret information segment can be represented by one video sequence in the SCVD according to the mapping table to accomplish the data hiding and extraction. Experimental results show that the proposed method performs much better in capacity, robustness, and security than the state-of-the-art methods. It is worth mentioning that the proposed method overcomes the security issue of transmitting a large amount of auxiliary information in coverless video steganographic algorithms.

Many Computer-Generated (CG) images are spreading widely on the Internet, which may deliberately misinform or deceive the public. Therefore, distinguishing CG images from natural photographic (PG) has become a frontier research topic in the field of image forensics. Although many algorithms have been proposed, it is still very challenging to detect CG images generated by the recent cutting-edge generative methods. Besides, most existing algorithms tend to generalize poorly when facing different unseen multimodal generative models. To address this issue, a novel method based on amplified texture differences learning is proposed to tackle this problem. We first design a deep texture enhancement module for discriminative texture amplification. Specifically, a semantic segmentation module is utilized to generate semantic segmentation map for the affine transformation operation guidance, which can be further used to recover the texture in different regions of the input image. Then, the combination of the original image and the high-frequency components of the original and enhanced images are fed into a hybrid neural network equipped with attention mechanisms, which refines intermediate features and facilitates trace exploration in spatial and channel dimensions respectively. By verifying on several commonly used benchmark datasets and a newly constructed dataset11The benchmark is available at https://github.com/191578010/DSGCG. with more realistic and diverse images, the experimental results demonstrate that the proposed approach outperforms some existing methods.

High Efficiency Video Coding (HEVC) double compression detection is of prime significance in video forensics. However, double compression with the same parameters and video content with high motion displacement intensity have become two main factors that limit the performance of existing algorithms. To address these issues, a novel motion-adaptive algorithm is proposed in this paper. Firstly, the analysis of GOP structure in HEVC standard and the coding process of HEVC double compression are provided. Next, sub-features composed of fluctuation intensities of intra prediction modes and unstable Prediction Units (PUs) in normal Intra-Frames (I-frames) and optical flow in adaptive I-frames are exploited in our algorithm. Each sub-feature is extracted during the process of multiple decompression. We further combine these sub-features into a 27-dimensional detection feature, which is finally fed to the Support Vector Machine (SVM) classifier. By following a separation-fusion detection strategy, the experimental result shows that the proposed algorithm outperforms the existing state-of-the-art methods and demonstrates superior robustness to various motion displacement intensities and a wide variety of coding parameter settings.

The emergence of the high-efficiency video coding (HEVC) standard enables people to enjoy high definition (HD) video content; meanwhile, HD videos, tamper detection has become a crucial issue and gradually aroused people's attention. The detection of double HEVC compressed videos with the same coding parameters is challenging since the recompression traces are inconspicuous. To deal with this issue, a novel method based on the intra prediction mode is proposed in this paper. First, the quality degradation mechanism is analyzed to facilitate the selection of classification features and the source of error in intra coding is fully considered to establish the equivalent error model. Second, the feature model of double HEVC compression detection, which is mainly based on the statistical feature of intra prediction mode, is proposed. Finally, the experiment is carried out in 720p and 1080p HEVC videos instead of low-resolution (CIF or QCIF) videos. Experimental results have demonstrated better efficiency of the proposed method in comparison to the state-of-the-art methods. Besides, the proposed method is more robust to various encoding configurations.