arXiv subjects

Maninder Singh

Publications and source records attributed to Maninder Singh.

6 recordsLinked to original sources

arXiv2026

The Illusion of Secure LLM Code: Closing the Security Gap via Iterative Reprompting

Large Language Models (LLMs) are increasingly integrated into software development workflows, yet their ability to autonomously generate secure authentication code remains uncertain. This paper evaluates the security architecture of authentication systems generated by five prominent AI coding assistants through a bi-modal assessment framework combining static code analysis and dynamic penetration testing, mapped to NIST SP 800-63B guidelines. The study examines model behavior across four prompting strategies Basic, Secure, NIST-Based, and Reprompting to reflect varying levels of developer guidance. Empirical results demonstrate that code generated from functional or generically secure prompts consistently omits critical protections, particularly concerning brute-force resistance, session management, and robust password handling. While providing explicit, single-shot NIST context significantly improves compliance, the findings reveal that this remains structurally inadequate. Instead, iterative Reprompting: forcing models into a contextual self-auditing loop is strictly required to achieve a comprehensive, defense-in-depth security architecture. Ultimately, this study proves that current AI coding assistants do not produce secure-by-default applications, dictating that enterprise deployments must transition from single-shot prompt engineering to continuous, standards-driven verification pipelines.

cs.CR↗

arXiv2026

BEACON: A Multimodal Dataset for Learning Behavioral Fingerprints from Gameplay Data

Continuous authentication in high-stakes digital environments requires datasets with fine-grained behavioral signals under realistic cognitive and motor demands. But current benchmarks are often limited by small scale, unimodal sensing or lack of synchronised environmental context. To address this gap, this paper introduces BEACON (Behavioral Engine for Authentication & Continuous Monitoring), a large-scale multimodal dataset that captures diverse skill tiers in competitive Valorant gameplay. BEACON contains approximately 430 GB of synchronised modality data (461 GB total on-disk including auxiliary Valorant configuration captures) from 79 sessions across 28 distinct players, estimated at 102.51 hours of active gameplay, including high-frequency mouse dynamics, keystroke events, network packet captures, screen recordings, hardware metadata, and in-game configuration context. BEACON leverages the high precision motor skills and high cognitive load that are inherent to tactical shooters, making it a rigorous stress test for the robustness of behavioral biometrics. The dataset allows for the study of continuous authentication, behavioral profiling, user drift and multimodal representation learning in a high-fidelity esports setting. The authors release the dataset and code on Hugging Face and GitHub to create a reproducible benchmark for evaluating next-generation behavioral fingerprinting and security models.

cs.CR↗

arXiv2026

ReVision : A Post-Hoc, Vision-Based Technique for Replacing Unacceptable Concepts in Image Generation Pipeline

Image-generative models are widely deployed across industries. Recent studies show that they can be exploited to produce unacceptable content. Existing mitigation strategies rely on prompt filtering and safety-aware training, both of which can be bypassed and often degrade generative quality. In this work, we propose ReVision, a training-free, prompt-based, post-hoc safety framework for image-generation pipeline. ReVision acts as a post-generation safeguard by analyzing generated images and selectively editing unsafe concepts without altering the underlying generator. Prior post-hoc editing methods often rely on imprecise spatial localization, limiting deployability, in multi-concept scenes. To address this limitation, ReVision introduces a VLM-assisted spatial gating mechanism for instance-consistent localization, enabling integrity-preserving edits. We introduce an 800-image benchmark spanning single- and multi-unsafe-concept images, each composed alongside benign concepts in shared scenes. On this benchmark, ReVision improves CLIP alignment toward safe prompts by +0.121, reduces multi-concept background LPIPS from 0.166 to 0.058, and eliminates NudeNet detections (70.51 -> 0). Across external benchmarks, ReVision outperforms prior methods, and a human study shows it reduces recognizability of unacceptable content from 96% to 10%.

cs.CR↗

arXiv2025

Advanced Real-Time Fraud Detection Using RAG-Based LLMs

Artificial Intelligence has become a double edged sword in modern society being both a boon and a bane. While it empowers individuals it also enables malicious actors to perpetrate scams such as fraudulent phone calls and user impersonations. This growing threat necessitates a robust system to protect individuals In this paper we introduce a novel real time fraud detection mechanism using Retrieval Augmented Generation technology to address this challenge on two fronts. First our system incorporates a continuously updating policy checking feature that transcribes phone calls in real time and uses RAG based models to verify that the caller is not soliciting private information thus ensuring transparency and the authenticity of the conversation. Second we implement a real time user impersonation check with a two step verification process to confirm the callers identity ensuring accountability. A key innovation of our system is the ability to update policies without retraining the entire model enhancing its adaptability. We validated our RAG based approach using synthetic call recordings achieving an accuracy of 97.98 percent and an F1score of 97.44 percent with 100 calls outperforming state of the art methods. This robust and flexible fraud detection system is well suited for real world deployment.

cs.CR↗

arXiv2023

Quantum Information Science and Technology for Nuclear Physics. Input into U.S. Long-Range Planning, 2023

In preparation for the 2023 NSAC Long Range Plan (LRP), members of the Nuclear Science community gathered to discuss the current state of, and plans for further leveraging opportunities in, QIST in NP research at the Quantum Information Science for U.S. Nuclear Physics Long Range Planning workshop, held in Santa Fe, New Mexico on January 31 - February 1, 2023. The workshop included 45 in-person participants and 53 remote attendees. The outcome of the workshop identified strategic plans and requirements for the next 5-10 years to advance quantum sensing and quantum simulations within NP, and to develop a diverse quantum-ready workforce. The plans include resolutions endorsed by the participants to address the compelling scientific opportunities at the intersections of NP and QIST. These endorsements are aligned with similar affirmations by the LRP Computational Nuclear Physics and AI/ML Workshop, the Nuclear Structure, Reactions, and Astrophysics LRP Town Hall, and the Fundamental Symmetries, Neutrons, and Neutrinos LRP Town Hall communities.

nucl-ex↗

arXiv2014

Analysis of RSA algorithm using GPU programming

Modern-day computer security relies heavily on cryptography as a means to protect the data that we have become increasingly reliant on. The main research in computer security domain is how to enhance the speed of RSA algorithm. The computing capability of Graphic Processing Unit as a co-processor of the CPU can leverage massive-parallelism. This paper presents a novel algorithm for calculating modulo value that can process large power of numbers which otherwise are not supported by built-in data types. First the traditional algorithm is studied. Secondly, the parallelized RSA algorithm is designed using CUDA framework. Thirdly, the designed algorithm is realized for small prime numbers and large prime number . As a result the main fundamental problem of RSA algorithm such as speed and use of poor or small prime numbers that has led to significant security holes, despite the RSA algorithm's mathematical soundness can be alleviated by this algorithm.

cs.CR↗