arXiv subjects

Bikash Saha

Publications and source records attributed to Bikash Saha.

11 recordsLinked to original sources

arXiv2026

PROPARAG: An Evidence-Grounded Decision Support System for Cybersecurity Policy Assessment

Cybersecurity policy assessment is an evidence-intensive organizational decision task. Reviewers must locate relevant policy statements, determine whether they sufficiently address security controls, identify missing elements, and decide where further policy action is required. Existing AI-based approaches support parts of this process, but often provide limited support for evidence verification, partial coverage, and diagnostic review. We present PROPARAG, an evidence-grounded decision-support framework for control-level cybersecurity policy assessment. PROPARAG retrieves relevant policy evidence, assigns full, partial, or absent coverage, identifies policy gaps, generates corrective recommendations, and provides evidence-linked explanations for expert review. We evaluate the framework on 1,007 NIST SP~800-53 controls across two real-world organizational policy corpora. PROPARAG achieves F1-scores of 88.54% and 82.31%, and outperforms the strongest evaluated baseline. Semantic evidence retrieval provides substantial gains, while structured assessment further improves performance over single-stage analysis. Expert evaluation also shows strong gap correctness and evidence groundedness. The results suggest that effective policy-assessment support also benefits from evidence provenance, explicit intermediate states, diagnostic information, and human reviewability. Evidence provenance, explicit intermediate states, structured diagnosis, and human reviewability are important parts of the assessment process.

cs.CR↗

arXiv2026

Neutron-Induced Enhancement of Ion Transport Through Lithium-Ion Battery Materials

Polycrystalline solid-state ionic conductors (SSICs) are essential energy materials for all-solid-state Li-ion batteries. To date, achieving a room-temperature ionic conductivity of solid electrolytes comparable to that of their liquid counterparts remains a critical challenge. Here, we experimentally demonstrate that thermal neutron irradiation can offer an innovative strategy in that neutron-induced modification in an SSIC model (LiBO$_{2}$ as an effective cathode coating) can facilitate ion transport through the material, enhancing its ionic conductivity. The central concept is that high-flux ($\sim 10^{9}\text{ neutrons}\cdot \text{cm}^{-2}\cdot \text{s}^{-1}$) thermal neutrons ($\sim \text{25 meV}$) selectively transmute strong neutron absorbers [which are $^{10}$B (3840 barns) and $^{6}$Li (940 barns) isotopes and present in their natural abundances of $\sim 19.9\%$ and $\sim 7.5\%$, respectively, in polycrystalline grains of LiBO$_2$] to generate lattice vacancies without compromising their crystallographic long-range order. In addition, by-product gamma photons emitted from $^{10}$B transmutation free electrons to stop atomic displacement and simultaneously neutralize the space charge built up by positively-charged oxygen vacancies at grain boundaries. As a result, the ionic conductivity is increased by nearly 20\% for the grains and more than 80\% for the grain boundaries. This study validates theoretical predictions and highlights a vital strategy for boosting ion transport in ionic solids. Overall, this novel approach establishes a new revenue for broader applications and greater enhancements of advanced functional materials in their related solid-state ionic devices, including all-solid-state lithium-ion batteries.

cond-mat.mtrl-sci↗

arXiv2025

MalGEN: A Testbed for Modeling and Evaluating Malware Behaviors

Modern cybersecurity requires systematic ways to evaluate how detection systems respond to evolving and previously unseen attack behaviors. Existing malware repositories largely capture known patterns and provide limited support for stress-testing defenses against novel threats. To address this, we present MalGEN, a modular testbed that models adversarial workflows and generates executable artifacts in a controlled environment. The framework decomposes high-level attack objectives into structured stages, enabling the synthesis of diverse and multi-stage behaviors. We evaluate MalGEN across 1,920 benchmark settings covering multiple platforms and behavioral objectives, resulting in 977 executable samples. Analysis shows that the generated artifacts exhibit a wide range of malicious techniques and multi-stage attack patterns. However, 45.71% of these samples remain undetected by existing detection engines, which reveals notable gaps in current defenses. These findings provide practical insights into the limitations of widely used detection approaches and support the development of more robust security evaluation and testing practices.

cs.CR↗

arXiv2025

Generative AI in Financial Institution: A Global Survey of Opportunities, Threats, and Regulation

Generative Artificial Intelligence (GenAI) is rapidly reshaping the global financial landscape, offering unprecedented opportunities to enhance customer engagement, automate complex workflows, and extract actionable insights from vast financial data. This survey provides an overview of GenAI adoption across the financial ecosystem, examining how banks, insurers, asset managers, and fintech startups worldwide are integrating large language models and other generative tools into their operations. From AI-powered virtual assistants and personalized financial advisory to fraud detection and compliance automation, GenAI is driving innovation across functions. However, this transformation comes with significant cybersecurity and ethical risks. We discuss emerging threats such as AI-generated phishing, deepfake-enabled fraud, and adversarial attacks on AI systems, as well as concerns around bias, opacity, and data misuse. The evolving global regulatory landscape is explored in depth, including initiatives by major financial regulators and international efforts to develop risk-based AI governance. Finally, we propose best practices for secure and responsible adoption - including explainability techniques, adversarial testing, auditability, and human oversight. Drawing from academic literature, industry case studies, and policy frameworks, this chapter offers a perspective on how the financial sector can harness GenAI's transformative potential while navigating the complex risks it introduces.

cs.CR↗

arXiv2025

MaLAware: Automating the Comprehension of Malicious Software Behaviours using Large Language Models (LLMs)

Current malware (malicious software) analysis tools focus on detection and family classification but fail to provide clear and actionable narrative insights into the malignant activity of the malware. Therefore, there is a need for a tool that translates raw malware data into human-readable descriptions. Developing such a tool accelerates incident response, reduces malware analysts' cognitive load, and enables individuals having limited technical expertise to understand malicious software behaviour. With this objective, we present MaLAware, which automatically summarizes the full spectrum of malicious activity of malware executables. MaLAware processes Cuckoo Sandbox-generated reports using large language models (LLMs) to correlate malignant activities and generate concise summaries explaining malware behaviour. We evaluate the tool's performance on five open-source LLMs. The evaluation uses the human-written malware behaviour description dataset as ground truth. The model's performance is measured using 11 extensive performance metrics, which boosts the confidence of MaLAware's effectiveness. The current version of the tool, i.e., MaLAware, supports Qwen2.5-7B, Llama2-7B, Llama3.1-8B, Mistral-7B, and Falcon-7B, along with the quantization feature for resource-constrained environments. MaLAware lays a foundation for future research in malware behavior explanation, and its extensive evaluation demonstrates LLMs' ability to narrate malware behavior in an actionable and comprehensive manner.

cs.CR↗

arXiv2024

Automated Classification of Cybercrime Complaints using Transformer-based Language Models for Hinglish Texts

The rise in cybercrime and the complexity of multilingual and code-mixed complaints present significant challenges for law enforcement and cybersecurity agencies. These organizations need automated, scalable methods to identify crime types, enabling efficient processing and prioritization of large complaint volumes. Manual triaging is inefficient, and traditional machine learning methods fail to capture the semantic and contextual nuances of textual cybercrime complaints. Moreover, the lack of publicly available datasets and privacy concerns hinder the research to present robust solutions. To address these challenges, we propose a framework for automated cybercrime complaint classification. The framework leverages Hinglish-adapted transformers, such as HingBERT and HingRoBERTa, to handle code-mixed inputs effectively. We employ the real-world dataset provided by Indian Cybercrime Coordination Centre (I4C) during CyberGuard AI Hackathon 2024. We employ GenAI open source model-based data augmentation method to address class imbalance. We also employ privacy-aware preprocessing to ensure compliance with ethical standards while maintaining data integrity. Our solution achieves significant performance improvements, with HingRoBERTa attaining an accuracy of 74.41% and an F1-score of 71.49%. We also develop ready-to-use tool by integrating Django REST backend with a modern frontend. The developed tool is scalable and ready for real-world deployment in platforms like the National Cyber Crime Reporting Portal. This work bridges critical gaps in cybercrime complaint management, offering a scalable, privacy-conscious, and adaptable solution for modern cybersecurity challenges.

cs.CR↗

arXiv2024

Chasing the Shadows: TTPs in Action to Attribute Advanced Persistent Threats

The current state of Advanced Persistent Threats (APT) attribution primarily relies on time-consuming manual processes. These include mapping incident artifacts onto threat attribution frameworks and employing expert reasoning to uncover the most likely responsible APT groups. This research aims to assist the threat analyst in the attribution process by presenting an attribution method named CAPTAIN (Comprehensive Advanced Persistent Threat AttrIbutioN). This novel APT attribution approach leverages the Tactics, Techniques, and Procedures (TTPs) employed by various APT groups in past attacks. CAPTAIN follows two significant development steps: baseline establishment and similarity measure for attack pattern matching. This method starts by maintaining a TTP database of APTs seen in past attacks as baseline behaviour of threat groups. The attribution process leverages the contextual information added by TTP sequences, which reflects the sequence of behaviours threat actors demonstrated during the attack on different kill-chain stages. Then, it compares the provided TTPs with established baseline to identify the most closely matching threat group. CAPTAIN introduces a novel similarity measure for APT group attack-pattern matching that calculates the similarity between TTP sequences. The proposed approach outperforms traditional similarity measures like Cosine, Euclidean, and Longest Common Subsequence (LCS) in performing attribution. Overall, CAPTAIN performs attribution with the precision of 61.36% (top-1) and 69.98% (top-2), surpassing the existing state-of-the-art attribution methods.

cs.CR↗

arXiv2024

A Comprehensive Survey of Advanced Persistent Threat Attribution: Taxonomy, Methods, Challenges and Open Research Problems

Advanced Persistent Threat (APT) attribution is a critical challenge in cybersecurity and implies the process of accurately identifying the perpetrators behind sophisticated cyber attacks. It can significantly enhance defense mechanisms and inform strategic responses. With the growing prominence of artificial intelligence (AI) and machine learning (ML) techniques, researchers are increasingly focused on developing automated solutions to link cyber threats to responsible actors, moving away from traditional manual methods. Previous literature on automated threat attribution lacks a systematic review of automated methods and relevant artifacts that can aid in the attribution process. To address these gaps and provide context on the current state of threat attribution, we present a comprehensive survey of automated APT attribution. The presented survey starts with understanding the dispersed artifacts and provides a comprehensive taxonomy of the artifacts that aid in attribution. We comprehensively review and present the classification of the available attribution datasets and current automated APT attribution methods. Further, we raise critical comments on current literature methods, discuss challenges in automated attribution, and direct toward open research problems. This survey reveals significant opportunities for future research in APT attribution to address current gaps and challenges. By identifying strengths and limitations in current practices, this survey provides a foundation for future research and development in automated, reliable, and actionable APT attribution methods.

cs.CR↗

arXiv2024

Structural modulation driven Curie temperature enhancement in Cr-doped SrRuO3

Strongly correlated system with competing ground states are often poised close to the quantum critical point. External perturbations such as pressure, strain, electric field, and chemical doping can stabilise its ground state with exotic physical properties. Cr-doping is the lone exception which enhances the Curie-temperature in one of such correlated system SrRuO$_3$. To find the origin of $T_C$ enhancement, we investigate temperature-dependent structure, spectroscopic, magnetic and magnetotransport properties in SrRu$_{1-x}$Cr$_x$O$_3$. Cr-doping squeezes the unit cell volume which effectively enhances the stretching octahedral distortion by nearly five times than pure SrRuO$_3$. The Curie temperature increment by $\sim$ 22 K for x = 0.15 is found to be intertwined with the structural-modulation. Temperature-dependent Neutron diffraction analysis indicate that the unit cell volume minima coincide exactly with the enhanced ferromagnetic ordering ($\sim$ 190 K). Further analysis reveals that the effect of Cr-doping not only freezes the octahedral tilt below 100 K but also suppresses the complex magnetism responsible for exchange bias and topological hall effect in SrRuO$_3$. The spectroscopic measurements find a reduction of itinerancy of d-electrons with Cr-doping. The magnetotransport measurements portray an evolution from itinerant to localised ferromagnetism.

cond-mat.str-el↗

arXiv2024

TTPXHunter: Actionable Threat Intelligence Extraction as TTPs from Finished Cyber Threat Reports

Understanding the modus operandi of adversaries aids organizations in employing efficient defensive strategies and sharing intelligence in the community. This knowledge is often present in unstructured natural language text within threat analysis reports. A translation tool is needed to interpret the modus operandi explained in the sentences of the threat report and translate it into a structured format. This research introduces a methodology named TTPXHunter for the automated extraction of threat intelligence in terms of Tactics, Techniques, and Procedures (TTPs) from finished cyber threat reports. It leverages cyber domain-specific state-of-the-art natural language processing (NLP) to augment sentences for minority class TTPs and refine pinpointing the TTPs in threat analysis reports significantly. The knowledge of threat intelligence in terms of TTPs is essential for comprehensively understanding cyber threats and enhancing detection and mitigation strategies. We create two datasets: an augmented sentence-TTP dataset of 39,296 samples and a 149 real-world cyber threat intelligence report-to-TTP dataset. Further, we evaluate TTPXHunter on the augmented sentence dataset and the cyber threat reports. The TTPXHunter achieves the highest performance of 92.42% f1-score on the augmented dataset, and it also outperforms existing state-of-the-art solutions in TTP extraction by achieving an f1-score of 97.09% when evaluated over the report dataset. TTPXHunter significantly improves cybersecurity threat intelligence by offering quick, actionable insights into attacker behaviors. This advancement automates threat intelligence analysis, providing a crucial tool for cybersecurity professionals fighting cyber threats.

cs.CR↗

arXiv2021

Mechanism of Na-ionic conduction in the high efficient layered battery material Na2Mn3O7

The ionic conduction properties of the technologically important two-dimensional (2D) layered battery material Na2Mn3O7, with exceptional small-voltage hysteresis between charge and discharge curves, have been investigated as a function of temperature and frequency by an impedance spectroscopy. The detailed analyses of the impedance data in the form of dc-conductivity, ac-conductivity, electrical modulus, dielectric constant and complex polarizability reveal a long-range Na-ionic conductivity with negligible contribution from a local dipole relaxation. A significant enhancement (~10^4 times) of the Na-ion conductivity has been found with the increasing temperature from 353 K to 713 K. The temperature dependent conductivity reveals thermally activated conduction process with activation energies of 0.161 and 0.377 eV over the two temperature regions of 383-518 K and 518-713 K, respectively. AC conductivity study reveals a long-range hopping process for the conduction of charge carriers with a sharp increase of the hopping range at 518 K. The scaling study of the ac-conductivity reveals that the frequency-activated conductivity (above 10^4 Hz at 353 K) is mainly controlled by the critical frequency that increases with the increasing temperature. The Na-ion conduction in Na2Mn3O7 occurs predominantly by a correlated barrier hopping process. Besides, a correlation between ionic conduction and crystal structure has been established by x-ray and neutron diffraction study. We have further shown that the conductivity of Na2Mn3O7 can be enhanced by reduction of the stacking faults in the crystal structure. Our study facilitates the understanding of the microscopic ionic conduction mechanism in the highly efficient 2D battery material Na2Mn3O7 having high energy storage capacity and high structural stability, paving way for the discovery of materials for battery applications.

cond-mat.mtrl-sci↗