Data Assurance and Communication Security

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.

Subgraph matching, a cornerstone of relational pattern detection in domains ranging from biochemical systems to social network analysis, faces significant computational challenges due to the dramatically growing search space. Existing methods address this problem within a filtering-ordering-enumeration framework, in which the enumeration stage recursively matches the query graph against the candidate subgraphs of the data graph. However, the lack of awareness of subgraph structural patterns leads to a costly brute-force enumeration, thereby critically motivating the need for intelligent navigation in subgraph matching. To address this challenge, we propose Neural Graph Navigation (NeuGN), a neuro-heuristic framework that transforms brute-force enumeration into neural-guided search by integrating neural navigation mechanisms into the core enumeration process. By preserving heuristic-based completeness guarantees while incorporating neural intelligence, NeuGN significantly reduces the First Match Steps by up to 98.2% compared to state-of-the-art methods across six real-world datasets.

BackgroundThe rapid evolution of large language models (LLMs) has ushered in a new era of artificial intelligence (AI) with unprecedented capabilities in understanding and generating human-like text. This progress has sparked a burgeoning interest in applying LLMs across diverse fields, including healthcare. However, the use of LLMs in mental health remains a complex area that demands rigorous investigation. This systematic scoping review aims to explore the current landscape of LLM applications in mental health, identify key research trends and gaps, and delineate the ethical and practical boundaries, thereby providing a comprehensive framework for future research and clinical practice.MethodsThis study adheres to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. A comprehensive search was conducted across eleven databases (Web of Science, Scopus, PubMed, Medline, CINAHL, Cochrane, ACM Digital Library, IEEE Xplore, ScienceDirect, APA PsycInfo, and Google Scholar). A total of 29 articles were ultimately included in the study.ResultsThe application of LLMs in mental health is strategically focused on high-throughput screening and clinical augmentation. The application landscape is characterized by domain specialization, with the focus shifting from general models to specialized BERT models to achieve higher clinical accuracy, particularly for high-prevalence disorders such as depression and high-risk conditions. Data analysis is powered by massive, unstructured corpora from social media, supplemented by the systematic incorporation of structured clinical knowledge. However, significant limitations exist, including insufficient cultural sensitivity in non-Western contexts, challenges in capturing longitudinal patient history, and critical risks related to model value alignment and the generation of clinically misleading information.ConclusionLLMs have emerged as sophisticated “Mental Health Agents” with immense potential for providing personalized, knowledge-guided interventions. The core challenge for future development is to transcend basic functionality and achieve clinical rigor. Future research must prioritize deep specialization into psychological models, enhance multimodal integration for comprehensive patient assessment, and urgently develop robust ethical and cultural adaptation frameworks to ensure the models are safe, globally equitable, and reliable for clinical deployment, thereby fulfilling their potential to alleviate the global mental health resource crisis.

Mesh generation is a necessary pre-processing step in computational fluid dynamics. Recent advancements in deep learning have enhanced mesh generation capabilities. However, most existing methods rely on data-driven training, which is constrained by the high cost of acquiring high-quality mesh datasets. Data-free methods effectively address the cost issue of dataset construction but have difficulty fitting boundary conditions properly, making the generated meshes unacceptable for practical engineering scenarios. To overcome this limitation, this paper presents MeshAFN, a self-supervised approach for structured mesh generation. MeshAFN introduces an attention-based Fourier network to enhance feature extraction while optimizing mesh quality. By incorporating attention mechanisms and Fourier series into the feature extraction layer, MeshAFN effectively captures critical geometric characteristics. Furthermore, a novel loss function is designed based on the Navier–Lamé and Laplace equations to learn mapping between the computational domain and the physical domain, ensuring that the generated meshes strictly meet physical constraints and boundary conditions. Experimental results demonstrate that MeshAFN achieves superior mesh quality and fewer model parameters in mesh generation tasks.

The rapid development of the Internet of Things technology has led to a boom in the adoption of intelligent healthcare management systems in the healthcare industry. However, it has also highlighted key issues such as security, privacy, and efficient query of medical data. Traditional methods for querying medical data suffer from severe data leakage risks, low query performance, and excessive storage space. This article proposes a comprehensive Secure ENcrypted Search for Health Scheme (SENSH) solution based on consortium blockchain and searchable encryption to address these challenges. SENSH enables efficient authorization management through Bloom filters, ensuring fast querying of large datasets by authorized users while saving storage space. It uses off-chain Advanced Encryption Standard (AES) and on-chain storage management for data protection, significantly reducing the likelihood of data exposure. The system is also enhanced with event triggering and logging mechanisms to support real-time monitoring and data tracing to meet audit compliance requirements. It provides version control and timestamping to accommodate dynamic data updates, employs an obfuscationfactor to prevent tag-based original data content leakage, and supports dynamic updating of tags to accommodate different access requirements. Experimental results show that SENSH excels in authorization management, privacy protection, defense against tampering, and anti-replay and Distributed Denial of Service (DDoS). Compared with existing schemes, SENSH has significant advantages in terms of gas consumption, computation cost, and execution time. It is particularly suited for the protection and efficient query of medical and health data.

With the continuous advancement of industrial intelligence, the closed environment of industrial control network is becoming more and more open, and the intranet equipment of industrial control system is facing more risks. In recent years, more attention has been paid to the safety of industrial control network. In order to improve the safety detection efficiency and accuracy of industrial control network and enhance the ability of industrial control network to resist risks, the identification of industrial control equipment types in the network is the foundation. In order to solve the problem that some industrial control equipment can't identify the type of equipment by active detection because they don't give feedback to the received detection packets after setting relevant rules or strategies, this paper constructs a knowledge map of the connectivity between different types of equipment, and then infers the types of other equipment with the connectivity with identifiable types of equipment on the basis of identifying some equipment types in the network.

As Artificial Intelligence advances, it plays an increasingly important role in identifying and detecting Internet threats to various applications to ensure cyber security, such as sensor data, financial data, unusual patterns in text sequences, and anomalies in ECG data. A number of deep learning approaches based on auto encoders have been developed to detect network anomalies and improve network security posture. Existing methods Auto Encoders models for network anomaly detection vary in performance without offering a comprehensive approach to understand the critical impacts of the core set of performance indicators of Auto Encoder models. In this research article, the proposed Long Short Term Memory (LSTM) autoencoder uses the capabilities of both LSTM networks and autoencoders in a specialized deep learning architecture. LSTM autoencoder is an advanced neural network architecture that employs Long Short Term memory (LSTM) units to encode input data into a lower dimensional format and subsequently decode it, primarily aimed at recognizing data patterns and identifying anomalies based on reconstruction error. The quantifiable disparity between the original input data and the data recreated by an autoencoder; a significant error typically signifies the presence of an anomaly when the model has been trained on normative data. Proposed model capable to protect "Zeroday" threat detector can be trained on normal data patterns, and any significant deviation in the reconstruction indicates potential threats. Based on the experimental results, we have been able to detect anomalies ranging from 90% to 99% in various malware types. In addition, this work observed that proposed LSTM auto encoder model achieved better results when compared with existing RNN model classification scenarios.

Personality prediction via different techniques is an established and trending topic in psychology. The advancement of machine learning algorithms in multiple fields also attracted the attention of Automatic Personality Prediction (APP). This research proposes a novel TraitBertGCN method with a data fusion technique for predicting personality traits. Initially, this work integrates a pre-trained language model, Bidirectional Encoder Representations from Transformers (BERT), with a three-layer Graph Convolutional Network (GCN) to leverage large-scale language understanding and graph-based learning for personality prediction. This study fuses the two datasets (essays and myPersonality) to overcome the bias and generalize the model across different domains. We fine-tuned our TraitBertGCN model on the fused dataset and then evaluated it on both datasets individually to assess its adaptability and accuracy in varied contexts. We compared the proposed model’s results with previous studies; our model achieved better performance in personality trait prediction across multiple datasets, with an average accuracy of 77.42% on the essays dataset and 87.59% on the myPersonality dataset.