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.

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.

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.

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.

Recently, coverless steganography algorithms have attracted increased research attention due to their ability to completely resist steganalysis algorithms. However, the existing algorithms do not attain the same robust balance against geometric and non-geometric attacks. In addition, most of the existing methods need to transmit some auxiliary information along with the stego-images, which increases the cost of the hidden information. In this paper, a robust coverless image steganography algorithm based on a hash generation model is proposed. Different from the existing methods, the hash sequences are generated by an end-to-end CNN model, where the input is the original images, and the output is the corresponding hash sequences. Therefore, no auxiliary information needs to be transmitted when hiding the secret information. Moreover, the attention mechanism and adversarial training are introduced to improve the robustness of the model. The loss function is redesigned to accommodate these operations. Finally, an index structure is built to enhance the mapping efficiency. The experimental results show that the proposed method possesses better robustness and security compared with the state-of-the-art coverless image steganography algorithms.

The steganography research of videos leads to excellent communication methods for transmitting secret message, and high efficiency video coding(HEVC) video is one popular steganographic carrier. This article proposes a prediction unit(PU) based wide residual-net steganography(PWRN) for HEVC videos. The visual quality distortion of modifying PUs is theoretically analyzed, which illustrates that modifying PUs only has a little negative effect on visual quality. Therefore, the data hiding method in this article allows to modify all types of PUs except for$2N\times 2N$to each other according to the secret data. In this way, high embedding efficiency is achieved, and the PU distributions in stego-videos can be kept similar to those of cover-videos, which is essential for resisting steganalysis. Meanwhile, a super-resolution convolutional neural network(CNN) with wide residual-net filter(WRNF) is proposed to replace the in-loop filter in HEVC for reconstructing I-pictures, which results in more precisely predicted P-pictures, and it further leads to less bitrate cost and better visual quality of stego-videos. The experimental results show that the proposed PWRN successfully resists the latest PU-targeted steganalysis algorithms, and compared with the state-of-the-art work, PWRN has achieved the lowest bitrate cost and the highest visual quality under the same capacity.