Advanced image generative models have led to concerns about malicious use, underscoring the necessity for generalizable detection methods. However, existing approaches tend to overfit to domain-specific forgery patterns, while overlooking complementary cues from different domains. Therefore, we introduce DySy-Det (Dynamic Synergy Detector), a novel framework that mines collaborative and robust forgery artifacts from multiple evidence domains. First, DySy-Det fine-tunes a CLIP vision transformer to extract high-level semantics for identifying conceptual inconsistencies, while generating attention maps that pinpoint key discriminative regions. Then, this semantic guidance, in the form of a mask, directs a targeted reconstruction process. By focusing on these salient areas, our approach effectively extracts localized reconstruction errors, thereby filtering out irrelevant background noise. Furthermore, inspired by the intrinsic generative mechanics of diffusion models, we introduce the concept of Reconstruction-Path Consistency (RPC), which quantifies the temporal stability of the denoising trajectory to expose dynamic generative artifacts. We capture this by computing noise alignment scores across multiple timesteps and encode them via a lightweight network. Extensive evaluations on GenImage and UniversalFakeDetect benchmarks demonstrate that DySy-Det outperforms the state-of-the-art detector by 6.14% and 1.57% in mean accuracy, respectively.

Multimodal language models (LMs) have shown significant potential for applications across various domains but remain vulnerable to adversarial attacks. Current research in white-box or black-box settings generally struggles with unrealistic attack assumptions and limited efficacy of targeted attacks. This paper introduces CoGA, a novel gray-box collaborative adversarial attack method for multimodal LMs. Under our gray-box settings, attackers have access only to the victim model’s input encoders. With the guidance of different modalities, we perturb the embedding representations from encoders to disrupt the semantic alignment across modalities, ultimately causing inaccurate outputs on various downstream tasks. Specifically, we integrate text embeddings into the loss calculations of the image attack and utilize image embeddings to guide the ranking of vulnerable words and the selection of final samples. Extensive experiments demonstrate that our method achieves superior attack performance across diverse models and tasks, suggesting the shared vulnerability of multimodal LMs in confronting adversarial challenges. Our work provides new insights into the security of multimodal LMs, facilitating the deployment of more robust and secure models in practical applications.

This work asks: with abundant, unlabeled real faces, how to learn a robust and transferable facial representation that boosts various face security tasks with respect to generalization performance? We make the first attempt and propose a self-supervised pretraining framework to learn fundamental representations of real face images, FSFM, that leverages the synergy between masked image modeling (MIM) and instance discrimination (ID). We explore various facial masking strategies for MIM and present a simple yet powerful CRFR-P masking, which explicitly forces the model to capture meaningful intra-region Consistency and challenging inter-region Coherency. Furthermore, we devise an ID network that naturally couples with MIM to establish underlying local-to-global Correspondence through tailored self-distillation. These three learning objectives, namely 3C, empower encoding both local features and global semantics of real faces. After pretraining, a vanilla ViT serves as a universal vision Foundation Model for downstream Face Security tasks: cross-dataset deepfake detection, cross-domain face anti-spoofing, and unseen diffusion facial forgery detection. Extensive experiments on 10 public datasets demonstrate that our model transfers better than supervised pretraining, visual and facial self-supervised learning arts, and even outperforms task-specialized SOTA methods.

Manipulating facial images results in negative influences on the social association, with deep generative models. Although many detection methods have been proposed, they have either designed sophisticated neural networks that lack enough interpretability, or found defects specific to one manipulation method. To address this issue, we propose a new approach to explore the defects of fake facial images after wavelet transform and call it GFS (Grayscale Frequency Statistics). First, we utilize Haar wavelet transformation to decompose the image into low-frequency approximation, horizontal detail, vertical detail, and diagonal detail. The GFS of real and fake images exhibit different distribution and forms in these four subbands. We qualitatively analyze these differences and quantify them as weights. Then, these four subband images are used to train four CNNs respectively, and the obtained detection results also verify the differences in GFS. After that, we combine the prediction results of the four CNNs and the corresponding weights to further improve the detection performance. We conduct extensive experiments on 11 datasets generated by various facial manipulation methods, and the superior results show the effectiveness of our proposed approach. Our findings indicate that the fake images generated by the current facial manipulation methods cannot simulate real images in wavelet-domain.

In a practical large scale antenna system (LSAS) over the millimeter Wave (mmWave) bands, the implementation of hybrid beamforming structure plays an important role as it provides high precoding gains to overcome the high path loss and achieve sufficient link margins. While employing such large antenna arrays, it becomes challenging to estimate the mmWave channel using the conventional algorithms. In this paper, we develop two novel multi-resolution mmWave channel estimation algorithms that exploit two dimensional discrete Fourier transform technique inspired by the sparse nature of the mmWave channel. The proposed algorithms take into account practical radio frequency (RF) hardware limitations and computational complexity reduction during the training phases. Numerical results indicate that the proposed algorithms can achieve a comparable spectral efficiency with respect to the case when perfect channel state information is known.

In this paper the millimeter wave (mmWave) single carrier transmission systems operating on wideband channels with frequency selectivity are considered. We propose two frequency selective hybrid precoding solutions, namely time delay compensation (TDC) based time domain equalization (TDE) and phase shift compensation (PSC) based frequency domain equalization (FDE). First, we implement a sectorized beamforming in RF domain to compensate the large path-loss at mmWave range and reduce the intra cluster delay spread. Here, the RF precoder is assumed to be frequency flat during one block transmission due to the independence of RF precoder design on the time delay spread. Subsequently, adopting TDC for TDE and PSC for FDE in digital baseband to reduce frequency selectivity, the baseband precoder is designed to maximize the achievable capacity. Finally, numerical results indicate that the proposed equalization algorithms can achieve a comparable performance with respect to the flat channel case.

Large scale antenna systems (LSAS) in the mmWave bands provide a solution to the problems of spectrum shortage experienced in the conventional microwave bands. In a practical large scale antenna deployment, implementation of hybrid beamforming structures is very important as it provides high array gains to overcome the high path loss and achieve sufficient link margins. However, while implementing this we encounter the challenges such as complexity, cost and energy consumption. In this paper a power consumption model for the large scale antenna mmWave system is presented and analysed. From the power consumption model we maximize the energy efficiency of the overall system. Optimization of energy efficiency is a crucial factor in system optimization and design of the powerhungry devices. But with increasing energy efficiency, the spectral efficiency decreases. Thus analysis of the relation between energy and spectral efficiency becomes a critical task and we optimize energy efficiency at a fixed spectral efficiency. The results can then be utilized to guide the practical energy/spectrum efficiency trade-off for the LSAS design.

The fading channel in mmWave communications has a very high chance to be frequency selective owing to the large transmission bandwidth. To overcome the frequency selectivity we propose a novel method, namely RF beamforming with time delay compensation. Simultaneously, baseband precoder at the transmitter side and the combiner at the receiver side are employed to maximize the capacity of the system. For effectively flattening the channel by beamforming on both sides, it is necessary to separate the individual rays. Motivated by achieving the best case beam separation, a signal-to-interference ratio (SIR) constrained capacity maximization algorithm is proposed in this paper. We also study the influence of the parameters such as the number of antennas at the transmitter side and the SIR threshold on the capacity and the system performance. Finally, the proposed method is validated by providing numerical examples by means of simulation.

Due to the very large transmission bandwidth of millimeter wave (mmWave) communications, the fading channel is expected to be frequency selective. Recent work in this field has mainly focused on cyclic-prefixed OFDM as a method to combat the frequency selectivity. But in this paper, we shift the focus on the novel method of time delay compensation to obtain a flat channel over wide bandwidth since it proves to be a more effective method reducing the computational complexity and achieving the high power efficiency at the receiver side. We employ time-shifted beams to compensate the delay spread and achieve high directionality. We also study the influence of physical parameters such as delay spread and system parameters such as the number of antennas on ergodic capacity and outage capacity. Finally, the proposed method is validated by providing numerical examples by means of simulation.

Millimeter wave (mmWave) band is characterized by very high path loss. To overcome this, spatial multiplexing and beamforming can be employed and in mmWave due to the small wavelength, large antenna arrays can be used to provide the required gain. However, unlike the traditional microwave systems it is not feasible to afford one RF chain per antenna. To overcome this practical limitation, hybrid beamforming can be utilized and the complexity of the transceiver can be reduced by implementing the RF domain processing using only the analog phase shifters. In this paper, we propose a two step approach to design a hybrid beamforming architecture. In this approach, we first design the baseband beamforming and then the RF domain beamforming is realized using an iterative algorithm. Finally, the proposed algorithm is validated by providing numerical examples by means of simulation.

When an iterative receiver has more than one iteration loop, scheduling the iterative decoding process is an important issue. To find the optimal scheduling, extrinsic information transfer (EXIT) function was the main tool in the literature. However, it is only very efficient when the codeword is significantly long. In this paper, under the consideration of a packet-based transmission scenario, we propose modeling the scheduling search problem as the foraging problem of ant colony. And then, an ant colony optimization (ACO) algorithm, labeled as max-min ant system (MMAS), is adopted and tailored for our problem. Simulation results show MMAS outperforms the EXIT function-based method when practical length codewords are used.