The advancement of deepfake technology has enabled deepfake audio to achieve unprecedented realism, posing significant challenges to automatic speaker verification (ASV) systems and threatening information security in critical sectors such as telecommunications and banking. As a countermeasure, Audio Deepfake Detection (ADD) has received growing attention in recent years. Existing ADD techniques derived from deep‐learning framework often encounter the problem of insufficient generalizability on unseen deepfake methods and insufficient robustness with changes to the codec and noise condition. To address these challenges, we propose an efficient method that adapts self‐supervised learning (SSL) model WavLM for deepfake detection. Instead of costly full‐model retraining, we introduce a lightweight “adapter” module, which acts as a small, trainable component to efficiently teach WavLM this new task. This adapter incorporates a Gaussian attention mechanism, which guides the model to consistently focus on subtle vocal artifacts and ignore irrelevant noise or compression distortions, thereby ensuring robust performance across different real‐world conditions. Extensive evaluations show that our framework not only achieves competitive performance on the ASVspoof 2019 LA and DF in‐domain benchmarks but, more importantly, excels in generalization. Our method achieves EERs of 6.11% on the challenging ‘in‐the‐wild’ dataset and 4.90% on the WaveFake dataset, outperforming existing methods against previously unseen deepfake attacks. This superior generalization is further explained through SHAP analysis, which reveals that our method enables the model to focus on discriminative information within voiced segments, effectively ignoring fragile ‘shortcut’ cues from silent portions that often hinder generalization in other systems.

As cloud services rapidly evolve and the demand for privacy protection grows, reversible data hiding in encrypted images (RDHEI) has gained significant attention. To enhance the data embedding capacity of RDHEI, this paper proposes an adaptive prediction-error entropy encoding framework that dynamically allocates edge-directed prediction (EDP) errors to either separate or grouped entropy coding modes, thereby optimizing net payload capacity. The image owner first predicts the pixel values of the cover image using EDP algorithm and calculates the prediction errors. After computing the prediction errors, the optimal thresholds are adaptively determined by minimizing the expected codeword length through entropy coding theory. Using these optimized thresholds, the prediction errors are classified into separate or grouped encoding categories, and losslessly compressed via arithmetic encoding. Through the processes of image encryption and self-embedding, an encrypted image with embedding room is generated and subsequently uploaded to the cloud server. The data hider can easily locate the data embedding room in the encrypted domain of the image and embed encrypted additional data to obtain the marked encrypted image. The authorized recipient can correctly extract the embedded data, restore the original plaintext image without any loss, or do both. The experimental results demonstrate the effectiveness of the proposed approach, surpassing many state-of-the-art RDHEI techniques.

Conventional time-delay neural networks (TDNNs) struggle to handle long-range context, their ability to represent speaker information is therefore limited for long utterances. Existing solutions either depend on increasing model complexity or try to strike a balance between local features and global context to address this issue. To effectively leverage the long-term dependencies of audio signals and constrain model complexity, we introduce a novel module called Global-aware Filter layer (GF layer) in this work, which employs a set of learnable transform-domain filters between a 1D discrete Fourier transform and its inverse transform to capture global context. Additionally, we develop a dynamic filtering strategy and a sparse regularization method to enhance the performance of the GF layer and prevent overfitting. Based on the GF layer, we present a dual-stream TDNN architecture called DS-TDNN for automatic speaker verification (ASV), which utilizes two unique branches to extract both local and global features in parallel and employs an efficient strategy to fuse different-scale information. Experiments on the Voxceleb and SITW databases demonstrate that the DS-TDNN achieves a relative improvement of 10% together with a relative decline of 20% in computational cost over the ECAPA-TDNN in the speaker verification task. This improvement becomes more evident as the utterance's duration grows. Furthermore, the DS-TDNN also beats popular deep residual models and attention-based systems on utterances of arbitrary length.

Eliminating the flickers in digital images captured by rolling shutter cameras is a fundamental and important task in computer vision applications. The flickering effect in a single image stems from the mechanism of asynchronous exposure of rolling shutters employed by cameras equipped with CMOS sensors. In an artificial lighting environment, the light intensity captured at different time intervals varies due to the fluctuation of the power grid, ultimately resulting in the flickering artifact in the image. Up to date, there are few studies related to single image deflickering. Further, it is even more challenging to remove flickers without a priori information, e.g., camera parameters or paired images. To address these challenges, we propose an unsupervised framework termed DeflickerCycleGAN, which is trained on unpaired images for end-to-end single image deflickering. Besides the cycle-consistency loss to maintain the similarity of image contents, we meticulously design another two novel loss functions, i.e., gradient loss and flicker loss, to reduce the risk of edge blurring and color distortion. Moreover, we provide a strategy to determine whether an image contains flickers or not without extra training, which leverages an ensemble methodology based on the output of two previously trained markovian discriminators. Extensive experiments on both synthetic and real datasets show that our proposed DeflickerCycleGAN not only achieves excellent performance on flicker removal in a single image but also shows high accuracy and competitive generalization ability on flicker detection, compared to that of a well-trained classifier based on ResNet50.

Detecting the presence of the electric network frequency (ENF) signal in audio recordings is a prerequisite of applying the ENF criterion that plays an essential role in numerous forensic applications. However, existing detection methods are powerless to handle short-duration audio recordings that have attracted considerable attention due to the popularity of voice messaging apps. This paper proposes a novel deep learning-based approach for ENF detection in short audio recordings, reducing the minimum operating range of audio duration to 1/10 of the state-of-the-art methods. Meanwhile, a convolutional attention network termed Conv-AttNet is proposed to improve the detection performance of convolutional neural networks (CNN) through the attention mechanism. Experiments on both synthetic and real-world audio recordings reveal that Conv-AttNet is able to detect the ENF signal buried in only 2 seconds of audio recordings, surpassing both matched filtering and typical CNN like ResNet50. In addition, the detection accuracy can be further increased by utilizing audio recordings of longer duration.

Identifying the model of a cell-phone with which an audio recording is made serves an important forensic purpose. In this paper, we propose a channel attention mechanism based on subband awareness to focus on the most relevant parts of the frequency bands to produce more efficient feature representations for cell-phone recognition task. A multi-stream network is introduced to fully exploit difference among frequency bands that provide critical clues to identify the fingerprints from the built-in microphones, and thus is able to recognize cell-phones from different manufacturers and even different models from the same manufacturer. The effectiveness of the proposed design is validated by a collection of speaker-independent audio recordings from 20 models of cell-phones made by 5 major manufacturers. In particular, the fusion of data augmentation and attention strategy greatly increases the robustness of the scheme when additive noise is present in the recorded audios. Finally, the salient regions infer the critical subbands for the recognition of different cell-phone models.

This paper addresses robust designs of secure simultaneous wireless information and power transfer for multiple-input single-output (MISO) multiuser systems. By using a bounded uncertainty model for the channel state information (CSI) from transmitters to legitimate receivers and under the assumption of only available statistic knowledge of the CSI to eavesdroppers, we consider the robust designs with both worst-case and chance-constrained optimizations. To jointly optimize transmit beamforming vectors and power splitting factors, we formulate three problems aiming at minimizing the system power, maximizing the sum secrecy rate, and maximizing the minimal secrecy rate, respectively, subject to both energy harvesting and secrecy outage constraints. These problems are intractable in their original forms due to the CSI models and their non-convexity. To reach computationally efficient solutions, we first rewrite the original problems by semi-definite relaxation, then transform the CSI uncertainty related constraints by S-procedure, and finally approximate the non-convex constraints by the first-order Taylor expansion. By the reformulations, we present iterative successive convex approximation algorithm for approaching the optimized solutions. Simulation results under various setups of system parameters are provided to examine the system performance and validate the effectiveness of the proposed schemes.

This article deals with the problem of Electric Network Frequency (ENF) estimation where Signal to Noise Ratio (SNR) is an essential challenge. By exploiting the low-rank structure of the ENF signal from the audio spectrogram, we propose an approach based on robust principle component analysis to get rid of the interference from speech contents and some of the background noise, which in our case can be regarded as sparse in nature. Weighted linear prediction is enforced on the low-rank signal subspace to gain accurate ENF estimation. The performance of the proposed scheme is analyzed and evaluated as a function of SNR, and the Cramér-Rao Lower Bound (CRLB) is approached at an SNR level above -10 dB. Experiments on real datasets have demonstrated the advantages of the proposed method over state-of-the-art work in terms of estimation accuracy. Specifically, the proposed scheme can effectively capture the ENF fluctuations along the time axis using small numbers of signal observations while preserving sufficient frequency precision.

Splicing, cutting and insertion are the most common operations imposed on audio files when the adversary intends to modify or fabricate the content. The detection of such kinds of tampering is still challenging in real-world applications. In this paper, a generic approach for the detection of audio tampering is proposed via the analysis of electric network frequency (ENF). Based on the fact that tampering with an audio leads to anomalous variations of the underlying ENF signal, a wavelet-filtered ENF signal is generated to highlight the abnormal ENF variations. An autoregressive (AR) model is then fitted to the detail part of the ENF signal and the resulting AR coefficients are employed to train the classifier under a supervised-learning framework. Experimental results show that our proposed method significantly outperforms the state-of-art methods in the context where moderate or high levels of noise are present. Moreover, robustness against MP3 compression can be achieved.

In this paper, we investigate how features can be effectively learned by deep neural networks for audio forensic problems. By providing a preliminary feature preprocessing based on electric network frequency (ENF) analysis, we propose a convolutional neural network (CNN) for training and classification of genuine and recaptured audio recordings. Hierarchical representations which contain levels of details of the ENF components are learned from the deep neural networks and can be used for further classification. The proposed method works for small audio clips of 2 second duration, whereas the state of the art may fail with such small audio clips. Experimental results demonstrate that the proposed network yields high detection accuracy with each ENF harmonic component represented as a single-channel input. The performance can be further improved by a combined input representation which incorporates both the fundamental ENF and its harmonics. The convergence property of the network and the effect of using an analysis window with various sizes are also studied. Performance comparison against the support tensor machine demonstrates the advantage of using CNN for the task of audio recapture detection. Moreover, visualization of the intermediate feature maps provides some insight into what the deep neural networks actually learn and how they make decisions.

Image resampling leaves behind periodical artifacts which are used as fingerprints for the forensics. A knowledgeable anti-forensic method erases such artifacts by irregular sampling. We observe that the irregular sampling followed by interpolation causes changes in local linear correlations, and propose a novel method to detect the anti-forensic method of resampling via partial autocorrelation coefficients. Experimental results on a large set of images show that the proposed method could effectively detect the anti-forensics of resampling with a low dimensional feature set.