arXiv subjects

Shafika Showkat Moni

Publications and source records attributed to Shafika Showkat Moni.

7 recordsLinked to original sources

arXiv2026

ChatGPT: Excellent Paper! Accept It. Editor: Imposter Found! Review Rejected

Large Language Models (LLMs) like ChatGPT are now widely used in writing and reviewing scientific papers. While this trend accelerates publication growth and reduces human workload, it also introduces serious risks. Papers written or reviewed by LLMs may lack real novelty, contain fabricated or biased results, or mislead downstream research that others depend on. Such issues can damage reputations, waste resources, and even endanger lives when flawed studies influence medical or safety-critical systems. This research explores both the offensive and defensive sides of this growing threat. On the attack side, we demonstrate how an author can inject hidden prompts inside a PDF that secretly guide or "jailbreak" LLM reviewers into giving overly positive feedback and biased acceptance. On the defense side, we propose an "inject-and-detect" strategy for editors, where invisible trigger prompts are embedded into papers; if a review repeats or reacts to these triggers, it reveals that the review was generated by an LLM, not a human. This method turns prompt injections from vulnerability into a verification tool. We outline our design, expected model behaviors, and ethical safeguards for deployment. The goal is to expose how fragile today's peer-review process becomes under LLM influence and how editorial awareness can help restore trust in scientific evaluation.

cs.CR↗

arXiv2025

Modeling Romanized Hindi and Bengali: Dataset Creation and Multilingual LLM Integration

The development of robust transliteration techniques to enhance the effectiveness of transforming Romanized scripts into native scripts is crucial for Natural Language Processing tasks, including sentiment analysis, speech recognition, information retrieval, and intelligent personal assistants. Despite significant advancements, state-of-the-art multilingual models still face challenges in handling Romanized script, where the Roman alphabet is adopted to represent the phonetic structure of diverse languages. Within the South Asian context, where the use of Romanized script for Indo-Aryan languages is widespread across social media and digital communication platforms, such usage continues to pose significant challenges for cutting-edge multilingual models. While a limited number of transliteration datasets and models are available for Indo-Aryan languages, they generally lack sufficient diversity in pronunciation and spelling variations, adequate code-mixed data for large language model (LLM) training, and low-resource adaptation. To address this research gap, we introduce a novel transliteration dataset for two popular Indo-Aryan languages, Hindi and Bengali, which are ranked as the 3rd and 7th most spoken languages worldwide. Our dataset comprises nearly 1.8 million Hindi and 1 million Bengali transliteration pairs. In addition to that, we pre-train a custom multilingual seq2seq LLM based on Marian architecture using the developed dataset. Experimental results demonstrate significant improvements compared to existing relevant models in terms of BLEU and CER metrics.

cs.CL↗

arXiv2025

An Efficient Privacy-preserving Intrusion Detection Scheme for UAV Swarm Networks

The rapid proliferation of unmanned aerial vehicles (UAVs) and their applications in diverse domains, such as surveillance, disaster management, agriculture, and defense, have revolutionized modern technology. While the potential benefits of swarm-based UAV networks are growing significantly, they are vulnerable to various security attacks that can jeopardize the overall mission success by degrading their performance, disrupting decision-making, and compromising the trajectory planning process. The Intrusion Detection System (IDS) plays a vital role in identifying potential security attacks to ensure the secure operation of UAV swarm networks. However, conventional IDS primarily focuses on binary classification with resource-intensive neural networks and faces challenges, including latency, privacy breaches, increased performance overhead, and model drift. This research aims to address these challenges by developing a novel lightweight and federated continuous learning-based IDS scheme. Our proposed model facilitates decentralized training across diverse UAV swarms to ensure data heterogeneity and privacy. The performance evaluation of our model demonstrates significant improvements, with classification accuracies of 99.45% on UKM-IDS, 99.99% on UAV-IDS, 96.85% on TLM-UAV dataset, and 98.05% on Cyber-Physical datasets.

cs.CR↗

arXiv2025

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation

Large Language Models (LLMs) are increasingly deployed in mission-critical systems, facilitating tasks such as satellite operations, command-and-control, military decision support, and cyber defense. Many of these systems are accessed through application programming interfaces (APIs). When such APIs lack robust access controls, they can expose full or top-k logits, creating a significant and often overlooked attack surface. Prior art has mainly focused on reconstructing the output projection layer or distilling surface-level behaviors. However, regenerating a black-box model under tight query constraints remains underexplored. We address that gap by introducing a constrained replication pipeline that transforms partial logit leakage into a functional deployable substitute model clone. Our two-stage approach (i) reconstructs the output projection matrix by collecting top-k logits from under 10k black-box queries via singular value decomposition (SVD) over the logits, then (ii) distills the remaining architecture into compact student models with varying transformer depths, trained on an open source dataset. A 6-layer student recreates 97.6% of the 6-layer teacher model's hidden-state geometry, with only a 7.31% perplexity increase, and a 7.58 Negative Log-Likelihood (NLL). A 4-layer variant achieves 17.1% faster inference and 18.1% parameter reduction with comparable performance. The entire attack completes in under 24 graphics processing unit (GPU) hours and avoids triggering API rate-limit defenses. These results demonstrate how quickly a cost-limited adversary can clone an LLM, underscoring the urgent need for hardened inference APIs and secure on-premise defense deployments.

cs.CR↗

arXiv2024

Blockchain-Enhanced Framework for Secure Third-Party Vendor Risk Management and Vigilant Security Controls

In an era of heightened digital interconnectedness, businesses increasingly rely on third-party vendors to enhance their operational capabilities. However, this growing dependency introduces significant security risks, making it crucial to develop a robust framework to mitigate potential vulnerabilities. This paper proposes a comprehensive secure framework for managing third-party vendor risk, integrating blockchain technology to ensure transparency, traceability, and immutability in vendor assessments and interactions. By leveraging blockchain, the framework enhances the integrity of vendor security audits, ensuring that vendor assessments remain up-to-date and tamperproof. This proposed framework leverages smart contracts to reduce human error while ensuring real-time monitoring of compliance and security controls. By evaluating critical security controls-such as data encryption, access control mechanisms, multi-factor authentication, and zero-trust architecture-this approach strengthens an organization's defense against emerging cyber threats. Additionally, continuous monitoring enabled by blockchain ensures the immutability and transparency of vendor compliance processes. In this paper, a case study on iHealth's transition to AWS Cloud demonstrates the practical implementation of the framework, showing a significant reduction in vulnerabilities and marked improvement in incident response times. Through the adoption of this blockchain-enabled approach, organizations can mitigate vendor risks, streamline compliance, and enhance their overall security posture.

cs.CR↗

arXiv2023

Integration of Digital Twin and Federated Learning for Securing Vehicular Internet of Things

In the present era of advanced technology, the Internet of Things (IoT) plays a crucial role in enabling smart connected environments. This includes various domains such as smart homes, smart healthcare, smart cities, smart vehicles, and many others.With ubiquitous smart connected devices and systems, a large amount of data associated with them is at a prime risk from malicious entities (e.g., users, devices, applications) in these systems. Innovative technologies, including cloud computing, Machine Learning (ML), and data analytics, support the development of anomaly detection models for the Vehicular Internet of Things (V-IoT), which encompasses collaborative automatic driving and enhanced transportation systems. However, traditional centralized anomaly detection models fail to provide better services for connected vehicles due to issues such as high latency, privacy leakage, performance overhead, and model drift. Recently, Federated Learning (FL) has gained significant recognition for its ability to address data privacy concerns in the IoT domain. Digital Twin (DT), proves beneficial in addressing uncertain crises and data security issues by creating a virtual replica that simulates various factors, including traffic trajectories, city policies, and vehicle utilization. However, the effectiveness of a V-IoT DT system heavily relies on the collection of long-term and high-quality data to make appropriate decisions. This paper introduces a Hierarchical Federated Learning (HFL) based anomaly detection model for V-IoT, aiming to enhance the accuracy of the model. Our proposed model integrates both DT and HFL approaches to create a comprehensive system for detecting malicious activities using an anomaly detection model. Additionally, real-world V-IoT use case scenarios are presented to demonstrate the application of the proposed model.

cs.CR↗

arXiv2022

Secure and Efficient Privacy-preserving Authentication Scheme using Cuckoo Filter in Remote Patient Monitoring Network

With the ubiquitous advancement in smart medical devices and systems, the potential of Remote Patient Monitoring (RPM) network is evolving in modern healthcare systems. The medical professionals (doctors, nurses, or medical experts) can access vitals and sensitive physiological information about the patients and provide proper treatment to improve the quality of life through the RPM network. However, the wireless nature of communication in the RPM network makes it challenging to design an efficient mechanism for secure communication. Many authentication schemes have been proposed in recent years to ensure the security of the RPM network. Pseudonym, digital signature, and Authenticated Key Exchange (AKE) protocols are used for the Internet of Medical Things (IoMT) to develop secure authorization and privacy-preserving communication. However, traditional authentication protocols face overhead challenges due to maintaining a large set of key-pairs or pseudonyms results on the hospital cloud server. In this research work, we identify this research gap and propose a novel secure and efficient privacy-preserving authentication scheme using cuckoo filters for the RPM network. The use of cuckoo filters in our proposed scheme provides an efficient way for mutual anonymous authentication and a secret shared key establishment process between medical professionals and patients. Moreover, we identify the misbehaving sensor nodes using a correlation-based anomaly detection model to establish secure communication. The security analysis and formal security validation using SPAN and AVISPA tools show the robustness of our proposed scheme against message modification attacks, replay attacks, and man-in-the-middle attacks.

cs.CR↗