Search Results (39)

Financial question answering is often treated as document question answering, although financial evidence is both multimodal and time-dependent. Semantically equivalent facts expressed in narrative text, tables, page images, or Extensible Business Reporting Language (XBRL) should support consistent answers, whereas a disclosure may support a query only after becoming public. We formalise this combination as crossmodal evidence symmetry under a causal temporal boundary and introduce TempFinRAG, a multimodal temporal retrieval-augmented generation (RAG) framework for point-in-time financial question answering. Given a question, company, and as-of date, the framework enforces the information boundary defined by U.S. Securities and Exchange Commission (SEC) filing availability; aligns page layout, text, table structure, and XBRL facts; retrieves time-valid evidence; executes auditable financial calculations; and generates a cited answer. A verifier checks temporal validity, claim support, numerical consistency, and the need to abstain. We further introduce TempFinQA, a point-in-time evaluation protocol built from public filings and XBRL facts, and evaluate the framework on complementary evidence-grounded, numerical, conversational, and multi-table benchmarks. On TempFinQA, TempFinRAG improves answer accuracy from 66.7% to 78.9% over hybrid RAG while reducing temporal evidence leakage from 10.8% to 1.7% and hallucination from 17.3% to 7.9%. Reliable financial question answering therefore requires consistent treatment across evidence representations and deliberately asymmetric access across time. Full article

Detecting known vulnerabilities in binary functions requires associating each function with relevant Common Vulnerabilities and Exposures (CVE) knowledge and determining the function’s state with respect to a specified CVE. Compilation obscures source-level semantics, while security patches often modify only a local check or control-flow condition. We present BinVulRAG, a function-level assessment framework that retrieves provenance-aware knowledge units rather than plain documents or code fragments. Each unit integrates vulnerability conditions, vulnerability and repair behavior, binary-difference evidence, and provenance metadata. During inference, given a target CVE, BinVulRAG retrieves relevant knowledge units and assesses vulnerability and repair behavior. The confidence-gating mechanism then assigns the final labels: vulnerable, non-vulnerable, or unknown. On 380 vulnerable–patched function pairs, BinVulRAG achieved F1 scores of 66.2% (vulnerable-class) and 59.1% (non-vulnerable-class), and a pair accuracy of 26.1%. These three metrics exceeded the corresponding best baseline values by 4.2, 11.2, and 12.2 percentage points, respectively. The ablation results show different precision–recall profiles across evidence configurations, indicating complementary roles for paired-binary evidence and structured vulnerability knowledge. These findings support grounding retrieved vulnerability knowledge in binary-observable evidence when distinguishing vulnerable functions from patched functions. Full article

In critical infrastructure environments, cybersecurity situation-awareness platforms generate large volumes of alerts, including substantial numbers of false positives, placing a considerable burden on security analysts. At present, alert correlation methods mainly rely on rule-based matching or statistical clustering, and large language models often lack the domain-specific threat intelligence required for reliable security analysis. This paper proposes GRAL, which is an AI-driven framework that combines graph neural networks (GNN) for cross-asset temporal alert correlation, retrieval-augmented generation (RAG) for dynamic threat intelligence enrichment, and large language models (LLM) for semantic reasoning and verdict generation. A temporal heterogeneous graph attention network constructs alert-relation graphs within a 72 h sliding window, and temporal decay and multi-relational dependencies are captured. Powered by bge-m3 embeddings and a dense vector index, the RAG module retrieves the most relevant threat intelligence entries above a cosine similarity threshold of 0.75. A domain-specific dataset of 1000 annotated security alerts from a nuclear power operational environment was built, and Cohen’s Kappa reached 0.87. The experiments show that GRAL achieves a macro-averaged precision of 87.0%, a macro-averaged recall of 97.0%, and a binary false-positive rate of 9.1%, together with 92.5% alert compression. Generalisation capability is confirmed by cross-dataset evaluation on CICIDS2017 (93.0% accuracy and 92.5% F1-score) and UNSW-NB15 (89.4% accuracy and 89.8% F1-score). Full article

English-teaching agents use external knowledge retrieval to update instructional content, broaden domain coverage, and personalize support beyond standalone large language models (LLMs). However, open sources may introduce harmful, biased, or misleading content into retrieval-augmented generation (RAG) pipelines, affecting learners’ judgment, cultural understanding, and value formation. To address this problem, this study proposes a multi-stage secure knowledge retrieval method for English-teaching agents. The method coordinates safeguards across knowledge-source access, retrieval execution, and model output. At the access stage, custom rules and Semgrep-based static scanning perform preliminary risk screening. At the retrieval stage, LLM-based dynamic evaluation identifies tool-description contamination and cross-file data-flow risks. At the output stage, semantic-embedding pre-screening, LLM review, and bounded knowledge purification detect and rewrite risky responses. Our experiments use public safety benchmarks, a mixed corpus of benign and poisoned passages, synthetic purification cases, and controlled end-to-end teaching scenarios. Compared with vanilla RAG, the framework reduces Poison Exposure@5 from 92.0% to 3.0% and retrieval attack success from 86.0% to 2.0% while preserving retrieval coverage. These results provide preliminary evidence that the framework can empower English teaching by enabling agents to deliver safer materials and trustworthy support for classroom questioning, academic writing, and intercultural learning. Full article

Modern railway maintenance is transitioning toward a condition-based maintenance system to stably operate the core infrastructure of sustainable smart cities. However, technical limitations remain in manually converting and analyzing massive amounts of inspection data into Building Information Modeling (BIM) objects. This causes information delays and technical severance in data-driven smart-city infrastructure. To address these challenges, this study proposes an Agentic BIM framework that integrates Large Language Model (LLM), Model Context Protocol (MCP), and Retrieval Augmented Generation (RAG) technologies. The proposed methodology standardizes the control channel between the LLM and BIM software through a central MCP server, while securing the accuracy of engineering judgments by utilizing the RAG pipeline to reference national railway-track-maintenance guidelines. System validation results demonstrated that geometric inspection data, including gauge and alignment, were automatically generated as BIM objects without human intervention. Furthermore, the maintenance grades and deadlines for sections exceeding thresholds were immediately highlighted within the model as visual attributes. Consequently, this framework proves an autonomous decision-making system that organically links inspection data with maintenance regulations. By transforming static, manual-labor-centered maintenance workflows into intelligent automated models, it increases the efficiency of railway infrastructure management while providing a scalable technical foundation for overall asset management of future smart-city infrastructure. Full article

The convergence of Information Technology (IT) and Operational Technology (OT) in Industry 4.0 has intensified the need for timely, trustworthy, and explainable cyber threat intelligence (CTI) for Industrial Control Systems (ICS). However, existing AI-enabled and Large Language Model (LLM)-based CTI solutions are predominantly designed for conventional IT environments and do not adequately address the safety, latency, governance, and operational constraints of industrial settings. This paper presents an AI-assisted CTI framework tailored to ICS and Industry 4.0 environments, integrating multi-source data ingestion, a Retrieval-Augmented Generation (RAG) knowledge store, a modular chain-of-agents architecture, and an explicit human-in-the-loop verification gate. Following a Design Science Research approach, the framework was evaluated through expert assessment involving twelve cybersecurity practitioners with experience in industrial and Security Operations Centre (SOC) environments and complemented by a proof-of-concept artefact instantiation based on the APT41 DUST campaign. The prototype integrated five heterogeneous CTI evidence sources and executed the automated analytical workflow in approximately 25 s (25.29 s) while illustrating evidence-grounded retrieval, specialized agent orchestration, and human-supervised intelligence generation. Practitioner feedback indicated that AI-assisted contextual intelligence and agent-based reasoning were perceived as valuable, while successful adoption depends primarily on governance, explainability, trust, and alignment with existing operational workflows rather than algorithmic sophistication alone. The study contributes a design-science artefact that combines retrieval-augmented intelligence, modular AI agents, and human oversight, providing practical design guidance for trustworthy AI-assisted CTI deployment in safety-critical Industry 4.0 environments. Full article

Large Language Models (LLMs) have significant potential in regulated domains such as law, healthcare, and compliance, where users need help interpreting complex rules and documents. However, these domains also make the risks of Large Language Models especially serious: a system may hallucinate legal authority, rely on outdated rules, mix jurisdictions, or expose sensitive information. Retrieval-Augmented Generation (RAG) reduces these risks by grounding the model’s answer in a curated document corpus, but standard RAG still does not guarantee that the retrieved sources are legally valid, up to date, applicable to the correct jurisdiction, or safe to use. In this paper, we present an ontology-governed approach to legal RAG. The central idea is to use a legal ontology not merely as background knowledge, but as an active control layer. Before retrieval, the ontology filters legal sources by jurisdiction, topic, lifecycle status, and temporal validity. After generation, validation rules check whether the answer is supported by approved evidence, cites valid legal sources, respects jurisdictional boundaries, and avoids unsafe or privacy-violating content. The system also records retrieval, validation, and response-generation steps in an audit trail to support later review. In this way, the proposed Legal Rule Auditor extends Graph RAG from a retrieval-enhancement technique into a governance architecture for legal question answering. Its goal is not simply to improve answer relevance, but to ensure that answers are legally grounded, trusted, current, jurisdictionally appropriate, and traceable. Full article

To address the issues of low intelligence and weak knowledge support in traditional water resource security risk analysis and response strategy generation, this paper proposes a novel framework based on hybrid retrieval augmentation and multi-agent collaboration. First, the proposed method integrates the DPSIR-CRITIC-TOPSIS framework with an obstacle degree model to construct an evaluation agent. This agent enables the intelligent assessment of regional water resource security and the precise extraction of key obstacle factors. Second, a water resource security knowledge graph and a vector knowledge base are constructed utilizing textual data, including policies and regulations, technical standards, the academic literature, and typical case studies. A hybrid retrieval augmentation mechanism—integrating graph reasoning, dual-path recall, and relation expansion—is designed to enhance the precision and relevance of the generated risk response strategies. Finally, a collaborative workflow comprising a master control agent alongside evaluation, retrieval, generation, and review agents is established to iteratively optimize the strategies through cross-validation and compliance reviews. In an empirical case study utilizing multi-year data from Henan Province and its 18 prefecture-level cities, experimental results demonstrate that the proposed method significantly outperforms baseline models across multi-dimensional semantic evaluation metrics, as well as BLEU-4 and ROUGE-L scores. The multi-agent collaborative architecture developed in this study, which integrates data-driven evaluation with knowledge-based hybrid retrieval augmentation, significantly elevates the intelligence level of water resource security assessment. It provides robust technical support for the analysis of regional water resource security situations and the intelligent generation of actionable response strategies. Full article

Information security compliance has become critical for organizations worldwide, with the ISO/IEC 27000 family serving as the most widely adopted framework for establishing information security management systems. Despite their global acceptance, these standards present significant interpretation challenges due to their formal language, abstract structure, and extensive cross-referencing across 97 documents. Traditional retrieval-augmented generation (RAG) systems, which rely on independent text chunking and dense vector retrieval, prove inadequate for such highly interconnected regulatory materials, often fragmenting contextual relationships and reducing accuracy. This study introduces a privacy-preserving RAG framework that integrates LightRAG, a knowledge graph-based retrieval system, with locally hosted open-source language models. Unlike chunk-based RAG systems that treat document segments independently, the system in this study constructs a semantic knowledge graph that explicitly models relationships between clauses through typed edges representing cross-references, semantic similarity, and hierarchical dependencies. To enable rigorous evaluation, we developed a curated benchmark dataset of 222 multiple-choice questions with authoritative ground-truth answers, systematically constructed from official ISO standards, certification preparation materials, and academic sources. Through systematic evaluation on this benchmark, we show that knowledge graph-based retrieval achieves higher accuracy than chunk-based RAG and non-retrieval LLM baselines within the evaluated setup. The analysis indicates that embedding model quality is strongly associated with system performance, that hybrid retrieval modes combining local and global graph traversal tend to yield better accuracy, and that mid-sized open-source models paired with strong retrievers can approach the performance of larger proprietary systems. The best configuration achieves 90.54% accuracy, demonstrating the promising effectiveness of graph-structured retrieval for multiple-choice regulatory questions. Full article

Traditional intrusion detection systems for IoT networks achieve high classification accuracy but lack interpretability and actionable incident-response capabilities, limiting their operational value in security-critical environments. This paper presents a graph-based multi-agent framework that integrates ensemble machine learning with Large Language Model (LLM)-powered incident report generation via Retrieval-Augmented Generation (RAG). The system employs a three-phase architecture: (1) a lightweight Random Forest binary pre-detection, achieving 99.49% accuracy with a 6 MB model size for edge deployment; (2) ensemble classification combining Multi-Layer Perceptron, Random Forest, and XGBoost with soft voting and SHAP-based feature attribution for explainability; and (3) a ReAct-based summary agent that synthesizes classification results with external threat intelligence from Web search and scholarly databases to generate evidence-grounded incident reports. To address the challenge of evaluating non-deterministic LLM outputs, we introduce custom RAG evaluation metrics—faithfulness and groundedness implemented via the LLM-as-Judge framework. Experimental validation on the ACI IoT Network Dataset 2023 demonstrates ensemble accuracy exceeding 99.8% across 11 attack classes; perfect groundedness scores (1.0), indicating all generated claims derive from the retrieved context; and moderate faithfulness (0.64), reflecting appropriate analytical synthesis. The ensemble approach mitigates individual model weaknesses, improving the UDP Flood F1 score from 48% (MLP alone) to 95% through soft voting. This work bridges the gap between high-accuracy detection and trustworthy, actionable security analysis for automated incident-response systems. Full article

Cybersecurity operations in IoT and edge environments require fast, evidence-grounded decisions under strict resource and trust constraints. While large language models can support triage and incident analysis, their parametric knowledge may be outdated and prone to hallucination. Retrieval-augmented generation (RAG) improves grounding by conditioning responses on retrieved evidence, but also introduces new risks such as knowledge-base poisoning, indirect prompt injection, and embedding leakage. Federated learning enables collaborative adaptation without centralizing sensitive data, motivating federated RAG (FedRAG) architectures for distributed cybersecurity deployments. This study presents a deployment-oriented scoping review of FedRAG for cybersecurity. The review follows PRISMA-ScR reporting guidance and synthesizes 82 studies published between 2020 and 2026, identified through keyword search and citation snowballing over OpenAlex, arXiv, and Crossref. We develop a taxonomy that clarifies the components of federated systems, deployment locations, trust boundaries, and protected assets. We further map the combined RAG+FL attack surface, summarize practical defenses and system patterns, and distill actionable guidance for secure, privacy-preserving, and efficient FedRAG deployment in real-world IoT and edge scenarios. Our synthesis highlights recurring trade-offs among robustness, privacy, latency, communication overhead, and maintainability, and identifies open research priorities in benchmark design, governance mechanisms, and cross-silo evaluation protocols for practical deployment. Full article

The RAG agentic architecture has demonstrated its ability to transform large language models (LLMs) into agents capable of planning, reasoning, and executing subtasks using external tools or APIs. In the financial sector, one of the main priorities when implementing new technologies—especially in systems like chatbots—is the protection of customer data and the need to maintain customer trust, making the challenges significant. This research presents a robust banking chatbot system that integrates RAG agentic architecture with specialized financial components, setting a new standard in the digital banking sector by prioritizing security, transparency, and functionality. The contributions of this work include the implementation of RAG agentic reasoning and self-correction financial components, and, primarily, the empirical study of the impact of a semantic firewall with online learning in financial RAG agentic systems, evaluated using public benchmarks and standard ranking metrics. Full article

Current research in consent management techniques focuses on isolated aspects of data security, privacy, or auditability, but important issues like (i) dynamically integrating regulatory updates into form generation, (ii) support in content generation with verifiable audit trails, and (iii) tools that make compliance reasoning transparent for non-legal users are not yet addressed. This paper introduces CONSENT, an architecture that integrates AI-based consent reasoning using Large Language Models (LLMs) for automated consent-form drafting and compliance evaluation, alongside blockchain technology for secure and auditable storage. The architecture builds on prior work to address the aforementioned issues by introducing three supporting mechanisms: (a) Specialized AI models coordinated through expert routing which coordinate subtasks such as automation in form generation and regulatory compliance, (b) Retrieval-Augmented Generation (RAG) that supports the integration of regulatory updates into forms, and (c) Explainable AI (XAI) for the reasoning behind form content and compliance assessments. CONSENT architecture is evaluated through 250 test cases and a pilot case study for clinical trial consent management involving 20 engineers and attorneys, who evaluated the prototype on form quality (i.e., coherence, conciseness, factuality, fluency, and relevance) as well as time and effort efficiency. Results show that CONSENT substantially reduces the manual effort in consent-form creation while providing transparent, audit-ready compliance assessments, highlighting its potential for dynamic, user-centric consent management. Full article

Maritime operations are increasingly reliant on sensor data to drive efficiency and enhance decision-making. However, despite rapid advances in large language models, including expanded context windows and stronger generative capabilities, critical industrial settings still require secure, role-constrained access to enterprise data and explicit limitation of model context. Retrieval-Augmented Generation (RAG) remains essential to enforce data minimization, preserve privacy, support verifiability, and meet regulatory obligations by retrieving only permissioned, provenance-tracked slices of information at query time. However, current RAG solutions lack robust validation protocols for numerical accuracy for high-stakes industrial applications. This paper introduces Lighthouse Bot, a novel Agentic RAG system specifically designed to provide natural-language access to complex maritime sensor data, including time-series and relational sensor data. The system addresses a critical need for verifiable autonomous data analysis within the Artificial Intelligence of Things (AIoT) domain, which we explore through a case study on optimizing ferry operations. We present a detailed architecture that integrates a Large Language Model with a specialized database and coding agents to transform natural language into executable tasks, enabling core AIoT capabilities such as generating Python code for time-series analysis, executing complex SQL queries on relational sensor databases, and automating workflows, while keeping sensitive data outside the prompt and ensuring auditable, policy-aligned tool use. To evaluate performance, we designed a test suite of 24 questions with ground-truth answers, categorized by query complexity (simple, moderate, complex) and data interaction type (retrieval, aggregation, analysis). Our results show robust, controlled data access with high factual fidelity: the proprietary Claude 3.7 achieved close to 90% overall factual correctness, while the open-source Qwen 72B achieved 66% overall and 99% on simple retrieval and aggregation queries. These findings underscore the need for a secure limited-context RAG in maritime AIoT and the potential for cost-effective automation of routine exploratory analyses. Full article

A universal approach to managing a person’s digital identity may be the single most important advancement to the Internet since its inception, promising the seamless flow of information, averting cybercrime, eliminating login credentials, and restoring privacy and trust through greater control of one’s identity online. However, this advancement brings significant risks, especially regarding personal privacy. It demands the meticulous development of digital identity infrastructure that balances robust data security measures with ethical handling of sensitive information, thereby safeguarding against misuse and unauthorised access. Currently, a consolidated vision for digital identity implementation remains unresolved, and aligning the different stakeholders’ motives and expectations is a challenging task. This article reviews and analyses the perspectives and expectations of four key stakeholder groups—government, business, academia, and consumers—regarding a digital identity ecosystem, aiming to increase trust in an eventual design framework. Using an online survey stratified across government, business, academia, and consumers, we identify areas of alignment and divergence regarding privacy, trust, usability, and governance expectations. We then encode these stakeholder expectations into a layered conceptual structure and illustrate its use as metadata for context-layered retrieval-augmented generation (RAG) in digital identity scenarios. Full article