Face normalization aims to enhance the robustness and effectiveness of face recognition systems by mitigating intra-personal variations in expressions, poses, occlusions, illuminations, and domains. Existing methods face limitations in handling multiple variations and adapting to cross-domain scenarios. To address these challenges, we propose a novel Unified Multi-Domain Face Normalization Network (UMFN) model, which can process face images with various types of facial variations from different domains, and reconstruct frontal, neutral-expression facial prototypes in the target domain. As an unsupervised domain adaptation model, UMFN facilitates concurrent training on multiple datasets across domains and demonstrates strong prototype reconstruction capabilities. Notably, UMFN serves as a joint prototype and feature learning framework, enabling the simultaneous extraction of domain-agnostic identity features through a decoupling mapping network and a feature domain classifier for adversarial training. Moreover, we design an efficient Heterogeneous Face Recognition (HFR) network that fuses domain-agnostic and identity-discriminative features for HFR, and introduce contrastive learning to enhance identity recognition accuracy. Empirical studies on diverse cross-domain face datasets validate the effectiveness of our proposed method.

Point cloud classifiers have been recently demonstrated to be vulnerable to backdoor attacks. The infected model functions normally on clean data, yet its predictions are errors when triggers are encountered. Currently, the point clean-label backdoor attack (PointCBA) method utilizes feature disentanglement, which is less effective for classes that are not in close proximity to the target class. This paper proposes a novel point cloud backdoor attack approach, named the point clean-label backdoor attack for specific classes (PointCBA-S). PointCBA-S incorporates a strategy named feature entanglement, designed to mitigate the feature similarity between proximate and target classes. This strategy ensures effectiveness across classes distant from the target class. Furthermore, a backdoor spatial optimization mechanism is utilized to create more potent triggers. Experiments indicate that PointCBA-S enhances the average attack success rate (ASR) by 30.8% under different classifiers.

Visual question answering models often rely on language priors in the training set, which affects their generalization ability when dealing with out-of-distribution test data. While existing research has improved model generalization by reducing biased samples, they may compromise model performance. Contrastive learning is a promising solution that uses positive samples with high similarity to a given text to guide the learning process. However, the positive samples are constrained by the size and diversity of existing datasets. We propose CLAP, Contrastive Learning with Answer Perturbation, to enhance model robustness. CLAP generates positive samples by constructing an answer dictionary based on question-image pairs, enabling the model to effectively cluster and differentiate various sample features. Additionally, CLAP introduces answer perturbation to reduce the model’s reliance on potential statistical shortcuts and enhance logical reasoning. Experiments demonstrate that CLAP significantly improves the model’s generalization and robustness while maintaining strong performance and achieving competitive performance. Our code is available at https://github.com/chenyong-cpu/CLAP.

Spatial-temporal data, fundamental to many intelligent applications, reveals dependencies indicating causal links between present measurements at specific locations and historical data at the same or other locations. Within this context, adaptive spatial-temporal graph neural networks (ASTGNNs) have emerged as valuable tools for modelling these dependencies, especially through a data-driven approach rather than pre-defined spatial graphs. While this approach offers higher accuracy, it presents increased computational demands. Addressing this challenge, this paper delves into the concept of localisation within ASTGNNs, introducing an innovative perspective that spatial dependencies should be dynamically evolving over time. We introduce DynAGS, a localised ASTGNN framework aimed at maximising efficiency and accuracy in distributed deployment. This framework integrates dynamic localisation, time-evolving spatial graphs, and personalised localisation, all orchestrated around the Dynamic Graph Generator, a light-weighted central module leveraging cross attention. The central module can integrate historical information in a node-independent manner to enhance the feature representation of nodes at the current moment. This improved feature representation is then used to generate a dynamic sparse graph without the need for costly data exchanges, and it supports personalised localisation. Performance assessments across two core ASTGNN architectures and nine real-world datasets from various applications reveal that DynAGS outshines current benchmarks, underscoring that the dynamic modelling of spatial dependencies can drastically improve model expressibility, flexibility, and system efficiency, especially in distributed settings. © 2025 Owner/Author.

The MQTT protocol, a protocol based on the pub/sub (publish/subscribe) model, is widely used in the field of IoT. However, it poses certain security risks in areas such as data encryption, identity authentication, and access control. Smart healthcare is an important application domain of the IoT. With the increasing aging population, large amounts of sensitive information require data protection. To address this, we design a framework specifically tailored to ensure end-to-end (E2E) security in IoT communications within smart healthcare, and it does not require ensuring that the broker is in a trusted state; it can operate with a public broker service. This framework incorporates three key management systems, thereby fulfilling the smart healthcare’s requirements for secure and efficient communications and ensuring that data transmission throughout the entire solution is encrypted. Furthermore, in order to ensure that our scheme can be applied in real-life scenarios, we used common IoT hardware devices to validate the proposed framework. Experimental results demonstrate that our framework can satisfy the criteria for E2E communication security.

With the rapid advancement of quantum computing, traditional public-key cryptosystems (e.g., RSA and ECC) are facing severe threats from quantum attacks (e.g., Shor’s algorithm). To address the demand for efficient and secure communication in resource-constrained scenarios such as the Internet of Things (IoT), this paper proposes an integrated quantum-resistant encryption and signature scheme based on polynomial ring lattices and accelerated by the Fast Fourier Transform (FFT). The scheme combines the Ring Learning With Errors (Ring-LWE) and Ring-LWE-Short Integer Solution (Ring-SIS) problems, optimizing operations over the polynomial ring Z q [ x ] / ( x N + 1 ) to significantly reduce key and ciphertext sizes. Additionally, FFT techniques are introduced to accelerate polynomial multiplication, while finite field FFT and floating-point error correction mechanisms address precision issues. Experimental results demonstrate that for polynomial degrees N ≥ 1024 , the encryption time is reduced by 23% compared to CRYSTALS-Kyber, with a 35% decrease in memory consumption. Moreover, Our signature verification mechanism demonstrates significantly lower resource consumption compared to both CRYSTALS-Dilithium and Falcon implementations under equivalent security parameters, making it suitable for low-overhead verification on edge devices and efficient signing on servers.

For generative learning tasks, there are three crucial criteria for generating samples from the models: quality, coverage/diversity, and sampling speed. Among the existing generative models, Generative adversarial networks (GANs) and diffusion models demonstrate outstanding quality performance while suffering from notable limitations. GANs can generate high-quality results and enable fast sampling, their drawbacks, however, lie in the limited diversity of the generated samples. On the other hand, diffusion models excel at generating high-quality results with a commendable diversity. Yet, its iterative generation process necessitates hundreds to thousands of sampling steps, leading to slow speeds that are impractical for real-time scenarios. To address the aforementioned problem, this paper proposes a novel Consistency-GAN model. In particular, to aid in the training of the GAN, we introduce instance noise, which employs consistency models using only a few steps compared to the conventional diffusion process. Our evaluations on various datasets indicate that our approach significantly accelerates sampling speeds compared to traditional diffusion models, while preserving sample quality and diversity. Furthermore, our approach also has better model coverage than traditional adversarial training methods.

The widespread adoption of deep neural networks (DNNs) is a testament to their profound impact on various domains. However, they are vulnerable to backdoor attacks. Previous defense strategies suffer from requiring additional prior knowledge or performance decreases. To tackle these challenges, we propose a new method to mitigate the impact of backdoor triggers. Specifically, we first devise a simple yet effective detection mechanism based on the region growing algorithm, which enables the identification of triggers within training data without necessitating prior knowledge. Then, we leverage the diffusion model to eliminate the inserted triggers while recovering the data information at the triggers’ locations. Finally, the processed data are fed into the current model for label recovery. Extensive experiments on the CIFAR10, Tiny Imagenet, and GTSRB datasets demonstrate that our method can defend against backdoor attacks effectively and surpasses the state-of-the-art defenses in terms of both main task accuracy (ACC) and backdoor task attack success rate (ASR).

In this paper, we present a novel method to significantly enhance the computational efficiency of Adaptive Spatial-Temporal Graph Neural Networks (ASTGNNs) by introducing the concept of the Graph Winning Ticket (GWT), derived from the Lottery Ticket Hypothesis (LTH). By adopting a pre-determined star topology as a GWT prior to training, we balance edge reduction with efficient information propagation, reducing computational demands while maintaining high model performance. Both the time and memory computational complexity of generating adaptive spatial-temporal graphs is significantly reduced from O(N2) to O(N). Our approach streamlines the ASTGNN deployment by eliminating the need for exhaustive training, pruning, and retraining cycles, and demonstrates empirically across various datasets that it is possible to achieve comparable performance to full models with substantially lower computational costs. Specifically, our approach enables training ASTGNNs on the largest scale spatial-temporal dataset using a single A6000 equipped with 48 GB of memory, overcoming the out-of-memory issue encountered during original training and even achieving state-of-the-art performance. Furthermore, we delve into the effectiveness of the GWT from the perspective of spectral graph theory, providing substantial theoretical support. This advancement not only proves the existence of efficient sub-networks within ASTGNNs but also broadens the applicability of the LTH in resource-constrained settings, marking a significant step forward in the field of graph neural networks. Code is available at https://anonymous.4open.science/r/paper-1430.

Traffic prediction poses a formidable challenge due to the dynamic and intricate spatial-temporal dependencies inherent in the task. Adaptive Spatial-Temporal Graph Neural Networks (ASTGNNs) have emerged as a promising solution, endeavoring to discern node-specific spatial patterns and autonomously deduce the spatial graphs among disparate traffic series. Nonetheless, the efficacy of existing ASTGNNs is often compromised as they struggle to apprehend the dynamic patterns of traffic series and deduce the dynamic spatial graphs in labyrinthine road networks, primarily due to their reliance on static node embeddings. In this paper, we introduce the Adaptive Dynamic Graph Convolutional Recurrent Network (ADGCRN), an innovative ASTGNN archetype adept at learning both dynamic spatial dependencies and dynamic spatial patterns from traffic data. Our model is distinguished by two instance-wise dynamic adaptive modules: i) the Instance-wise Dynamic Adaptive Graph Generation module, which integrates instance-wise state information and temporal periodicity into node embeddings; and ii) the Instance-wise Node Adaptive Parameter Learning module, which is capable of learning dynamic, instance-wise, and node-specific patterns for each traffic series. Rigorous experiments conducted on four benchmark datasets demonstrate that ADGCRN significantly outperforms the state-of-the-art ASTGNNs, achieving an average improvement of 3.45%, 3.11%, and 8.78% in terms of Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE), respectively.

Spatial-temporal graph models are prevailing for abstracting and modelling spatial and temporal dependencies. In this work, we ask the following question: whether and to what extent can we localise spatial-temporal graph models? We limit our scope to adaptive spatial-temporal graph neural networks (ASTGNNs), the state-of-the-art model architecture. Our approach to localisation involves sparsifying the spatial graph adjacency matrices. To this end, we propose Adaptive Graph Sparsification (AGS), a graph sparsification algorithm which successfully enables the localisation of ASTGNNs to an extreme extent (fully localisation). We apply AGS to two distinct ASTGNN architectures and nine spatial-temporal datasets. Intriguingly, we observe that spatial graphs in ASTGNNs can be sparsified by over 99.5% without any decline in test accuracy. Furthermore, even when ASTGNNs are fully localised, becoming graph-less and purely temporal, we record no drop in accuracy for the majority of tested datasets, with only minor accuracy deterioration observed in the remaining datasets. However, when the partially or fully localised ASTGNNs are reinitialised and retrained on the same data, there is a considerable and consistent drop in accuracy. Based on these observations, we reckon that (i) in the tested data, the information provided by the spatial dependencies is primarily included in the information provided by the temporal dependencies and, thus, can be essentially ignored for inference; and (ii) although the spatial dependencies provide redundant information, it is vital for the effective training of ASTGNNs and thus cannot be ignored during training. Furthermore, the localisation of ASTGNNs holds the potential to reduce the heavy computation overhead required on large-scale spatial-temporal data and further enable the distributed deployment of ASTGNNs.

Time series forecasting has widespread applications in urban life ranging from air quality monitoring to traffic analysis. However, accurate time series forecasting is challenging because real-world time series suffer from the distribution shift problem, where their statistical properties change over time. Despite extensive solutions to distribution shifts in domain adaptation or generalization, they fail to function effectively in unknown, constantly-changing distribution shifts, which are common in time series. In this paper, we propose Hyper TimeSeries Forecasting (HTSF), a hypernetwork-based framework for accurate time series forecasting under distribution shift. HTSF jointly learns the time-varying distributions and the corresponding forecasting models in an end-to-end fashion. Specifically, HTSF exploits the hyper layers to learn the best characterization of the distribution shifts, generating the model parameters for the main layers to make accurate predictions. We implement HTSF as an extensible framework that can incorporate diverse time series forecasting models such as RNNs. Extensive experiments on 7 benchmarks demonstrate that HTSF achieves state-of-the-art performances.

Pre-trained language models have been widely adopted as backbones in various natural language processing tasks.However, existing pre-trained language models ignore the descriptive meta-information in the text such as the distinction between the title and the mainbody, leading to over-weighted attention to insignificant text.In this paper, we propose a hypernetwork-based architecture to model the descriptive meta-information and integrate it into pre-trained language models.Evaluations on three natural language processing tasks show that our method notably improves the performance of pre-trained language models and achieves the state-of-the-art results on keyphrase extraction.

This study proposed a novel protective action for converter side phase-to-ground fault of FB-MMC-based bipolar HVDC. The faulty converter is kept in operation during fault, and its dc-link voltage reference is set to zero in order to avoid serious overvoltage of the sub-module capacitors. This protective action was verified by simulation. The overcurrent and overvoltage of converter arms are moderate when adopting this protective action.

Conventional Electromagnetic Transient (EMT) simulations of a Modular Multilevel Converter based HVDC (MMC-HVDC) is quite time consuming. Therefore, the sub modules are often modeled with equivalent transformation methods. In this paper, two equivalent models with much higher efficiency have been presented for a specific MMC topology, i.e. the diode clamped half bridge topology, which convenient the researches on MMC-HVDC with overhead lines. Details of the modeling technologies have been explained. Simulations have been carried out, focusing on computational efficiency, steady and transient performances. Compared to conventional EMT model, the proposed models are accurate enough, while with much higher efficiency.

This paper presents the dynamic performance test of a complete control and protection system for a Multi-terminal MMC HVDC system using hardware-in-the-loop (HIL) simulation. A novel HIL bench with a cost-effective input and output interface between the control system under test and the real-time simulator is introduced. Two critical test cases, namely the start-up of the MMC connected to islanded networks and the AC fault in the bus close to the MMC substation are studied. The validity of the proposed methodology for the dynamic performance test is confirmed by comparing the results from the HIL test and the actual waveform recorded from the field, after the MMC is commissioned.

High-voltage direct current system using modular multilevel converter (MMC-HVDC) is a potential candidate for grid integration of renewable energy over long distances. The dc-link fault is an issue MMC-HVDC must deal with. This paper proposed an enhanced MMC topology with dc fault ride-through capability. By using diode clamp sub-modules, the freewheeling effect of diodes is eliminated and fault currents can be very rapidly extinguished. Since the tripping of circuit breakers is avoided, MMC can immediately restart power transmission for non-permanent faults. The required rated voltage of additional semiconductors is half the conventional semiconductors, resulting in low extra cost. Simulation results using PSCAD/EMTDC have verified the validity of the proposed protection scheme.

Although arrays of SIMD PEs can be built with very high operating frequencies, problems exist in keeping the array busy. The inherent mismatch between host and array makes it difficult to maintain high array utilization: either the rate of instruction issue is very low or PE data locality is compromised, having the same effect. Our solution is based on an array control unit (ACU) design that expands macro instructions in two stages, first by data tile and then into microinstructions. The expansion itself solves the issue problem; decoupling the expansion modalities maintains data locality. Several issues involving host/ACU interaction need to be resolved to effect this solution.