Searcharxiv⌕ Search

arXiv subjects

Madhusudan Singh

Publications and source records attributed to Madhusudan Singh.

7 recordsLinked to original sources
arXiv2026

A Lightweight Ethereum Voting Prototype for Hospital Ethics Committees with Receipt-Based Inclusion Verification

This paper presents a Solidity, Hardhat, React, MetaMask, and ethers.js prototype for hospital ethics committee voting. Role controls, case-state checks, duplicate vote controls, and a receipt hash support public audit and transaction inclusion verification. Because vote events expose wallet addresses and vote values, the design provides pseudonymous auditability, not anonymous or secret-ballot voting; the receipt is neither receipt-free nor coercion-resistant. Evaluation reports 22 passing functional tests and local Hardhat gas use, including 284,137 gas per vote. A 12-participant simulation used assumed probabilities and is not human-subject evidence. Residual risks include multiple wallets, administrator or frontend compromise, credential reassignment, front-running, denial of service, and untested adversarial paths. Confidential deployment requires governed enrollment, encrypted ballots, independent audit, adversarial testing, reproducible benchmarks, and a real user study.

cs.CR↗
arXiv2026

Recognized but Not Produced: A Generation Benchmark for Culturally Specific Kinship Terms

Current literature evaluates large language models (LLMs) on multilingual kinship understanding using multiple choice benchmarks, treating it as a recognition problem. We instead prompt five open weight LLMs to generate kinship terms in three non Western languages (Hindi, Tamil, and Korean) across two communicative tasks and pair this with a matched option-supported selection baseline. On identical relation language cells, GPT OSS120B selects the correct term in 90.67% of 75 valid cells but produces an accepted term in 36.00% of the corresponding attempts; Llama 3.370B shows the same pattern (77.92% versus 24.24%). Since the four-option condition displays the candidate terms and does not require script production, the difference is interpreted as an evaluation format gap rather than direct proof that lexical knowledge is intact. On explicitly specified L3 prompts, accuracy varies sharply, from GLM-5.1 at 72.29% to Llama-3.370B at 24.24%. The paternal-lineage advantage is language specific; it is large in Hindi but weak or reversed in Korean, while Tamil shared-term pairs provide a control for measurement variation. These results show that culturally specific kinship generation remains difficult even when the relationship is explicitly stated and motivate generation-based evaluation alongside multiple-choice testing.

cs.CL↗
arXiv2026

Who Verifies the Benchmark? Decentralizing Trust in Large Language Model Evaluation

LLM benchmarks can build an organization's reputation and attract customers, but only when results are transparent and verifiable. Unverified claims that DeepSeek R1 outperformed OpenAI's o1 contributed to market panic on January 27, 2025, when Nvidia lost USD589 billion in market value. Yet vendor benchmarks often depend on an honor system. Academic reassessments and independent leaderboards have found undisclosed changes to proprietary models, contaminated training data, and selective reporting. LLM-as-a-judge methods scale evaluation by reducing human review. Studies, however, suggest that judges may show identity-aware bias, scoring an answer according to its source model rather than its quality. This bias has not been fully measured or corrected across politically sensitive, reasoning-intensive, and preference-based tasks. We examine this problem using seven verifier models: GPT-OSS 120B, Llama 3.3 70B, GLM 5.1, Qwen3 32B, DeepSeek V4 Pro, Mistral Large3, and Sarvam M. They score anonymous and identity-disclosed responses from three primary models on 58 factual, reasoning, political, and preference-based questions. Identity disclosure slightly raises scores for factual questions, moderately affects stress-reasoning tasks, and causes large changes for geopolitically sensitive topics. Notable results include GLM5.1 (+7.00 points, p = 0.0249) and Llama 3.3 70B (+1.56 points, p = 0.00). We also introduce a blockchain-based commit-reveal protocol using Autonomous Economic Agents on an Ethereum-compatible ledger. In Phase 1, each judge records a one-way hash of its score and a secret salt before candidate identities are revealed. In Phase 2, the identity and raw score are disclosed and verified on-chain. This creates a tamper-evident audit trail that separates blind evaluation from post-hoc claims and reduces the verification burden on independent researchers and leaderboard operators.

cs.AI↗
arXiv2026

Explainable Machine Learning for Phishing Detection on Heterogeneous Datasets with MCP-Enabled Deployment

With the growth in digital transformation and Internet usage, the Social Engineering techniques such as Phishing have become a major concern for the users and the organizations. Phishing attacks involve deceptive techniques to trick users into revealing confidential information that causes financial loss and reputation damage to organizations. According to report of Verizon, 36% of all data breaches involved phishing, highlighting the need for intelligent, adaptive, and explainable security mechanisms. This paper examines the efficiency of different machine learning algorithms in phishing detection on heterogeneous phishing datasets that include a publicly available UCI dataset, our generated datasets using tools such as EvilGinx and Zphisher, and AI generated datasets. Moreover, this work incorporates explainable AI (XAI) techniques such as Information Gain, SHAP (SHapley Additive Explanations), and LIME (Local Interpretable Model-Agnostic Explanations) to examine the most influential features impacting classification outcomes. To support practical deployment, this work also incorporates an MCP-based phishing URL detection system that offers real-time URL analysis, feature extraction, confidence-based classification, and AI-assisted security interpretation. The experimental results demonstrate that among classical models the highest accuracy is obtained by Logistic Regression at 92.44%, among ensemble models CatBoost achieved the highest accuracy at 95.01%, among neural network CNN achieved an accuracy of 94.02%, and among transformer-based models, DistilBERT got the highest accuracy at 99.78%

cs.CR↗
arXiv2017

Intelligent Vehicle-Trust Point: Reward based Intelligent Vehicle Communication using Blockchain

The Intelligent vehicle (IV) is experiencing revolutionary growth in research and industry, but it still suffers from many security vulnerabilities. Traditional security methods are incapable to provide secure IV communication. The major issues in IV communication, are trust, data accuracy and reliability of communication data in the communication channel. Blockchain technology works for the crypto currency, Bit-coin, which is recently used to build trust and reliability in peer-to-peer networks having similar topologies as IV Communication. In this paper, we are proposing, Intelligent Vehicle-Trust Point (IV-TP) mechanism for IV communication among IVs using Blockchain technology. The IVs communicated data provides security and reliability using our proposed IV-TP. Our IV-TP mechanism provides trustworthiness for vehicles behavior, and vehicles legal and illegal action. Our proposal presents a reward based system, an exchange of some IV-TP among IVs, during successful communication. For the data management of the IV-TP, we are using blockchain technology in the intelligent transportation system (ITS), which stores all IV-TP details of every vehicle and is accessed ubiquitously by IVs. In this paper, we evaluate our proposal with the help of intersection use case scenario for intelligent vehicles communication.

cs.CR↗
arXiv2017

Safety Requirement Specifications for Connected Vehicles

In the coming years, transportation system will be revamped in a manner that there will be more intelligent and autonomous vehicle phenomenon around us such as smart cars, auto driving system, etc. Some of automotive industries are already producing smart cars. However, the main concern of this paper is on the infrastructure for connected vehicles, which can support such intelligent transportation. Current transportation system lacks proper infrastructure to support connected vehicles. Hence, in this article, we have surveyed and analyzed the current transportation system in developed and developing countries. In contrast, we are going to introduce secure intelligent transportation (roadside) infrastructure that is user centric (Driver, Autonomous driver etc.) for connected vehicles. In this paper we present the basic requirements of safety engineering infrastructure of roadside infrastructure in ITS for connected vehicles. Connected vehicles has network infrastructure to communicate with vehicle-to-vehicle (V-to-V), vehicle-to-infrastructure (V-to-I), lane correction system, and traffic information system etc. The connected vehicle is a good model for learning demands of infrastructure for ITS process because the system having a lot of use-cases and we must understand relationship between public institutions, people, companies in order to proceed ITS System.

cs.CY↗
arXiv2017

Blockchain Based Intelligent Vehicle Data sharing Framework

The Intelligent vehicle (IV) is experiencing revolutionary growth in research and industry, but it still suffers from many security vulnerabilities. Traditional security methods are incapable to provide secure IV data sharing. The major issues in IV data sharing are trust, data accuracy and reliability of data sharing data in the communication channel. Blockchain technology works for the crypto currency, Bit-coin, which is recently used to build trust and reliability in peer-to-peer networks having similar topologies as IV Data sharing. In this paper, we have proposed Intelligent Vehicle data sharing we are proposing a trust environment based Intelligent Vehicle framework. In proposed framework, we have use the blockchain technology as backbone of the IV data-sharing environment. The blockchain technology is provide the trust environment between the vehicles with the based on proof of driving.

cs.CR↗