arXiv subjects

Ahmad Mohsin

Publications and source records attributed to Ahmad Mohsin.

14 recordsLinked to original sources

arXiv2026

NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced Manufacturing

The growing complexity of cyber-physical attack surfaces in advanced manufacturing has made cyber threat intelligence analysis increasingly difficult. Although large language models and retrieval-augmented generation have improved CTI workflows, text-based approaches remain vulnerable to hallucinations and provide limited support for structured reasoning over interconnected threats. Graph-based RAG reduces some of these limitations, but existing approaches often lack ontology-consistent multi-hop reasoning and transparent evidence tracing across heterogeneous cybersecurity data. This paper proposes a graph-grounded neuro-symbolic framework that integrates ontology-aware symbolic query generation, knowledge graph retrieval, and neural language generation to support accurate and explainable threat analysis across information technology and operational technology environments. The framework adopts a dual-large language model architecture: the first model translates natural-language questions into executable Cypher queries for symbolic graph retrieval, while the second generates answers strictly from the retrieved graph evidence. Experimental evaluation using publicly available cyber threat intelligence benchmarks shows consistent improvements over the published baseline in reasoning accuracy, while also reducing hallucinations, strengthening multi-hop reasoning, and improving robustness to adversarial perturbations. Runtime and explainability analyses further demonstrate that the framework maintains interactive inference performance and exposes graph-grounded reasoning artifacts that allow analysts to inspect and verify each stage of the analysis. Overall, the results highlight the potential of graph-grounded neuro-symbolic reasoning as a scalable, interpretable, and reliable approach to cyber threat intelligence for next-generation Industry 5.0 environments.

cs.CR↗

arXiv2026

DEFENGRAPH: Knowledge Graph-Enhanced LLMs for Blue Team Cyber Defense

Large Language Models (LLMs) show promise for supporting decision-making in cybersecurity, but their reliability in high-stakes, time-evolving environments remains limited due to hallucinations, poor temporal reasoning, and shallow grounding in system context. We introduce DEFENGRAPH, an LLM-driven assistant designed to support human defenders during cybersecurity incidents. DEFENGRAPH improves contextual reasoning by integrating a dual-layer Static-Dynamic Knowledge Graph (KG) with graph-based path retrieval, LLM-driven contextual filtering, and reasoning-based re-ranking. The framework grounds LLM outputs in both long-term domain knowledge and evolving event context, enabling faithful and temporally aware decision support. We evaluate DEFENGRAPH in a cyber defense setting using knowledge graphs constructed from heterogeneous security artifacts, including SIEM alerts, system topology, attacker behaviors, and prior defensive actions. The evaluation uses data collected during live Red vs. Blue team cyber range exercises simulating attacks on critical infrastructure, which generate realistic and noisy datasets reflecting real-world defender workflows and system dynamics. Evaluations across four prevalent LLMs show that DEFENGRAPH sets a new state-of-the-art: on GPT-4o it boosts reasoning-recall from 61.45\% to 73.49\% and ticket-action recall from 52.17% to 72.46% (precision 24.49\% to 29.24\%), with similar gains on LLaMA-3 (46.99\% to 61.45\%), DeepSeek-R1 (45.78\% to 56.63\%) and QWen-3 (51.81\% to 59.04\%), while surfacing up to 50 correct defense actions versus 36 for the next best baseline and holding fault rates steady.

cs.CR↗

arXiv2026

Enhancing LLMs with Context-Specific Knowledge for Mitigating Misinformation in SMEs: A RAG-based Modeling and Analysis

Large Language Models (LLMs), a part of artificial intelligence (AI), are increasingly being adopted by Small and Medium Enterprises (SMEs) to enhance question-answering capabilities and support business decision-making processes. However, hallucinations in LLM-generated outputs can serve as a source of misinformation, reducing user confidence in their reliability and trustworthiness within SMEs. Retrieval-Augmented Generation (RAG) has emerged as a promising approach to address this challenge by incorporating external knowledge sources into the modeling process. In this paper, we present VectorRAG and GraphRAG modeling approaches to mitigate hallucinations and misinformation risks and evaluate their effectiveness in SME environments. Our experimental evaluation is conducted on multiple state-of-the-art LLMs, including LLaMA, Mistral, and Qwen, to assess performance in terms of useful response generation, risk of hallucination, contextual relevance, as well as human-interpretation. The results demonstrate that RAG-enhanced LLMs can significantly improve response quality by reducing hallucinations and misinformation, thereby supporting more reliable, trustworthy, and context-aware decision-making in SME environments.

cs.AI↗

arXiv2026

Enhancing Adversarial Robustness in Network Intrusion Detection: A Layer-wise Adaptive Regularization Approach

The new wave of adversarial attacks that utilize gradient-related vulnerabilities in neural network-based classifiers makes Network Intrusion Detection Systems more open to such threats. Although state-of-the-art adversarial training methods have shown promising results in producing more robust classifiers, their interpretability and defense ability are limited due to their lack of understanding of how adversarial attacks propagate in different layers of network classifiers. In this paper, we present an insightful approach, called LARAR (Layer-wise Adversarial Robustness using Adaptive Regularization), that incorporates additional layer-wise vulnerability analysis and adaptive weighting in conventional adversarial training methods. Additionally, we utilize 'Auxiliary Classifiers' in our approach. LARAR provides interpretable layer-wise vulnerability scores, achieves a clean accuracy of 95.01%, and provides better robustness against adversarial attacks (FGSM, PGD, and transfer attacks) on the UNSW-NB15 dataset. Through the identification of vulnerable layers, the proposed framework reduces computational complexity and enables the early detection of adversarial samples, thus enhancing the effectiveness and interpretability of adversarial defense mechanisms in NIDS.

cs.CR↗

arXiv2026

TempoNet: Learning Realistic Communication and Timing Patterns for Network Traffic Simulation

Realistic network traffic simulation is critical for evaluating intrusion detection systems, stress-testing network protocols, and constructing high-fidelity environments for cybersecurity training. While attack traffic can often be layered into training environments using red-teaming or replay methods, generating authentic benign background traffic remains a core challenge -- particularly in simulating the complex temporal and communication dynamics of real-world networks. This paper introduces TempoNet, a novel generative model that combines multi-task learning with multi-mark temporal point processes to jointly model inter-arrival times and all packet- and flow-header fields. TempoNet captures fine-grained timing patterns and higher-order correlations such as host-pair behavior and seasonal trends, addressing key limitations of GAN-, LLM-, and Bayesian-based methods that fail to reproduce structured temporal variation. TempoNet produces temporally consistent, high-fidelity traces, validated on real-world datasets. Furthermore, we show that intrusion detection models trained on TempoNet-generated background traffic perform comparably to those trained on real data, validating its utility for real-world security applications.

cs.CR↗

arXiv2025

BRIDG-ICS: AI-Grounded Knowledge Graphs for Intelligent Threat Analytics in Industry~5.0 Cyber-Physical Systems

Industry 5.0's increasing integration of IT and OT systems is transforming industrial operations but also expanding the cyber-physical attack surface. Industrial Control Systems (ICS) face escalating security challenges as traditional siloed defences fail to provide coherent, cross-domain threat insights. We present BRIDG-ICS (BRIDge for Industrial Control Systems), an AI-driven Knowledge Graph (KG) framework for context-aware threat analysis and quantitative assessment of cyber resilience in smart manufacturing environments. BRIDG-ICS fuses heterogeneous industrial and cybersecurity data into an integrated Industrial Security Knowledge Graph linking assets, vulnerabilities, and adversarial behaviours with probabilistic risk metrics (e.g. exploit likelihood, attack cost). This unified graph representation enables multi-stage attack path simulation using graph-analytic techniques. To enrich the graph's semantic depth, the framework leverages Large Language Models (LLMs): domain-specific LLMs extract cybersecurity entities, predict relationships, and translate natural-language threat descriptions into structured graph triples, thereby populating the knowledge graph with missing associations and latent risk indicators. This unified AI-enriched KG supports multi-hop, causality-aware threat reasoning, improving visibility into complex attack chains and guiding data-driven mitigation. In simulated industrial scenarios, BRIDG-ICS scales well, reduces potential attack exposure, and can enhance cyber-physical system resilience in Industry 5.0 settings.

cs.CR↗

arXiv2025

SME-TEAM: Leveraging Trust and Ethics for Secure and Responsible Use of AI and LLMs in SMEs

Artificial Intelligence (AI) and Large Language Models (LLMs) are revolutionizing today's business practices; however, their adoption within small and medium-sized enterprises (SMEs) raises serious trust, ethical, and technical issues. In this perspective paper, we introduce a structured, multi-phased framework, "SME-TEAM" for the secure and responsible use of these technologies in SMEs. Based on a conceptual structure of four key pillars, i.e., Data, Algorithms, Human Oversight, and Model Architecture, SME-TEAM bridges theoretical ethical principles with operational practice, enhancing AI capabilities across a wide range of applications in SMEs. Ultimately, this paper provides a structured roadmap for the adoption of these emerging technologies, positioning trust and ethics as a driving force for resilience, competitiveness, and sustainable innovation within the area of business analytics and SMEs.

cs.LG↗

arXiv2025

A Unified Framework for Human AI Collaboration in Security Operations Centers with Trusted Autonomy

This article presents a structured framework for Human-AI collaboration in Security Operations Centers (SOCs), integrating AI autonomy, trust calibration, and Human-in-the-loop decision making. Existing frameworks in SOCs often focus narrowly on automation, lacking systematic structures to manage human oversight, trust calibration, and scalable autonomy with AI. Many assume static or binary autonomy settings, failing to account for the varied complexity, criticality, and risk across SOC tasks considering Humans and AI collaboration. To address these limitations, we propose a novel autonomy tiered framework grounded in five levels of AI autonomy from manual to fully autonomous, mapped to Human-in-the-Loop (HITL) roles and task-specific trust thresholds. This enables adaptive and explainable AI integration across core SOC functions, including monitoring, protection, threat detection, alert triage, and incident response. The proposed framework differentiates itself from previous research by creating formal connections between autonomy, trust, and HITL across various SOC levels, which allows for adaptive task distribution according to operational complexity and associated risks. The framework is exemplified through a simulated cyber range that features the cybersecurity AI-Avatar, a fine-tuned LLM-based SOC assistant. The AI-Avatar case study illustrates human-AI collaboration for SOC tasks, reducing alert fatigue, enhancing response coordination, and strategically calibrating trust. This research systematically presents both the theoretical and practical aspects and feasibility of designing next-generation cognitive SOCs that leverage AI not to replace but to enhance human decision-making.

cs.AI↗

arXiv2025

CyberAlly: Leveraging LLMs and Knowledge Graphs to Empower Cyber Defenders

The increasing frequency and sophistication of cyberattacks demand innovative approaches to strengthen defense capabilities. Training on live infrastructure poses significant risks to organizations, making secure, isolated cyber ranges an essential tool for conducting Red vs. Blue Team training events. These events enable security teams to refine their skills without impacting operational environments. While such training provides a strong foundation, the ever-evolving nature of cyber threats necessitates additional support for effective defense. To address this challenge, we introduce CyberAlly, a knowledge graph-enhanced AI assistant designed to enhance the efficiency and effectiveness of Blue Teams during incident response. Integrated into our cyber range alongside an open-source SIEM platform, CyberAlly monitors alerts, tracks Blue Team actions, and suggests tailored mitigation recommendations based on insights from prior Red vs. Blue Team exercises. This demonstration highlights the feasibility and impact of CyberAlly in augmenting incident response and equipping defenders to tackle evolving threats with greater precision and confidence.

cs.CR↗

arXiv2024

Can We Trust Large Language Models Generated Code? A Framework for In-Context Learning, Security Patterns, and Code Evaluations Across Diverse LLMs

Large Language Models (LLMs) such as ChatGPT and GitHub Copilot have revolutionized automated code generation in software engineering. However, as these models are increasingly utilized for software development, concerns have arisen regarding the security and quality of the generated code. These concerns stem from LLMs being primarily trained on publicly available code repositories and internet-based textual data, which may contain insecure code. This presents a significant risk of perpetuating vulnerabilities in the generated code, creating potential attack vectors for exploitation by malicious actors. Our research aims to tackle these issues by introducing a framework for secure behavioral learning of LLMs through In-Content Learning (ICL) patterns during the code generation process, followed by rigorous security evaluations. To achieve this, we have selected four diverse LLMs for experimentation. We have evaluated these coding LLMs across three programming languages and identified security vulnerabilities and code smells. The code is generated through ICL with curated problem sets and undergoes rigorous security testing to evaluate the overall quality and trustworthiness of the generated code. Our research indicates that ICL-driven one-shot and few-shot learning patterns can enhance code security, reducing vulnerabilities in various programming scenarios. Developers and researchers should know that LLMs have a limited understanding of security principles. This may lead to security breaches when the generated code is deployed in production systems. Our research highlights LLMs are a potential source of new vulnerabilities to the software supply chain. It is important to consider this when using LLMs for code generation. This research article offers insights into improving LLM security and encourages proactive use of LLMs for code generation to ensure software system safety.

cs.CR↗

arXiv2024

The Presence and the State-of-Practice of Software Architects in the Brazilian Industry -- A Survey

Context: Software architecture intensely impacts the software quality. Therefore, the professional assigned to carry out the design, maintenance and evolution of architectures needs to have certain knowledge and skills in order not to compromise the resulting application. Objective: The aim of this work is to understand the characteristics of the companies regarding the presence or absence of software architects in Brazil. Method: This work uses the Survey research as a means to collect evidence from professionals with the software architect profile, besides descriptive statistics and thematic analysis to analyze the results. Results: The study collected data from 105 professionals distributed in 24 Brazilian states. Results reveal that (i) not all companies have a software architect, (ii) in some cases, other professionals perform the activities of a software architect and (iii) there are companies that, even having a software architecture professional, have other roles also performing the duties of such a professional. Conclusions: Professionals hired as software architects have higher salaries than those hired in other roles that carry out such activity, although many of those other professionals still have duties that are typical of software architects.

cs.SE↗

arXiv2023

Digital Twins and the Future of their Use Enabling Shift Left and Shift Right Cybersecurity Operations

Digital Twins (DTs), optimize operations and monitor performance in Smart Critical Systems (SCS) domains like smart grids and manufacturing. DT-based cybersecurity solutions are in their infancy, lacking a unified strategy to overcome challenges spanning next three to five decades. These challenges include reliable data accessibility from Cyber-Physical Systems (CPS), operating in unpredictable environments. Reliable data sources are pivotal for intelligent cybersecurity operations aided with underlying modeling capabilities across the SCS lifecycle, necessitating a DT. To address these challenges, we propose Security Digital Twins (SDTs) collecting realtime data from CPS, requiring the Shift Left and Shift Right (SLSR) design paradigm for SDT to implement both design time and runtime cybersecurity operations. Incorporating virtual CPS components (VC) in Cloud/Edge, data fusion to SDT models is enabled with high reliability, providing threat insights and enhancing cyber resilience. VC-enabled SDT ensures accurate data feeds for security monitoring for both design and runtime. This design paradigm shift propagates innovative SDT modeling and analytics for securing future critical systems. This vision paper outlines intelligent SDT design through innovative techniques, exploring hybrid intelligence with data-driven and rule-based semantic SDT models. Various operational use cases are discussed for securing smart critical systems through underlying modeling and analytics capabilities.

cs.CR↗

arXiv2021

Expanding Frontiers: Settling an Understanding of Systems-of-Information Systems

System-of-Systems (SoS) has consolidated itself as a special type of software-intensive systems. As such, subtypes of SoS have also emerged, such as Cyber-Physical SoS (CPSoS) that are formed essentially of cyber-physical constituent systems and Systems-of-Information Systems (SoIS) that contain information systems as their constituents. In contrast to CPSoS that have been investigated and covered in the specialized literature, SoIS still lack critical discussion about their fundamentals. The main contribution of this paper is to present those fundamentals to set an understanding of SoIS. By offering a discussion and examining literature cases, we draw an essential settlement on SoIS definition, basics, and practical implications. The discussion herein presented results from research conducted on SoIS over the past years in interinstitutional and multinational research collaborations. The knowledge gathered in this paper arises from several scientific discussion meetings among the authors. As a result, we aim to contribute to the state of the art of SoIS besides paving the research avenues for the forthcoming years.

cs.SE↗

arXiv2019

A Taxonomy of Modeling Approaches for Systems-of-Systems Dynamic Architectures: Overview and Prospects

Systems-of-Systems (SoS) result from the collaboration of independent Constituent Systems (CSs) to achieve particular missions. CSs are not totally known at design time, and may also leave or join SoS at runtime, which turns the SoS architecture to be inherently dynamic, forming new architectural configurations and impacting the overall system quality attributes (i.e. performance, security and reliability). Therefore, it is vital to model and evaluate the impact of these stochastic architectural changes on SoS properties at abstract level at the early stage in order to analyze and select appropriate architectural design. Architectural description languages (ADL) have been proposed and used to deal with SoS dynamic architectures. However, we still envision gaps to be bridged and challenges to be addressed in the forthcoming years. This paper presents a broad discussion on the state-of-the-art notations to model and analyze SoS dynamic architectures. The main contribution this paper is threefold: (i) providing results of a literature review on the support of available architecture modeling approaches for SoS and an analysis of their semantic extension to support specification of SoS dynamic architectures, and (ii) a corresponding taxonomy for modeling SoS obtained as a result of the literature review. Besides, we also discuss future directions and challenges to be overcome in the forthcoming years.

cs.SE↗