Divya Guru

Mrs. Divya Guru

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 May 2021 in Electronics
Verified
Journal Article
Open access
PDF file
DGDivya Guru
Divya Guru
SPSupraja Perumal
Supraja Perumal
VVVijayakumar V.
Vijayakumar V.
A blockchain is a decentralized peer to peer platform which provides security services based on some key concepts, namely authentication, confidentiality, integrity and authorization. It is the process of recording and keeping track of the resources without the intervention of a centralized authority. This paper provides an overview of blockchains, the structure of blockchains, consensus algorithms, etc., It compares the algorithms based on their utility and limitations. Though blockchains provide secure communication, there are some minimal data leaks which are discussed. Various security issues in blockchains are discussed such as denial of service attacks, etc., In addition to security, some other blockchain challenges are presented like scalability, reliability, interoperability, privacy and consensus mechanisms for integration with AI, IoT and edge computing. This paper also explains about the importance of blockchains in the fields of smart healthcare, smart grid, and smart financial systems. Overall, this paper gives the glimpse of various protocols, algorithms, applications, challenges and opportunities that are found in the blockchain domain.

28 October 2024 in arXiv
Verified
Preprint
Open access
PDF file
SKSahasra Kokkula
Sahasra Kokkula
SRSomanathan R
Somanathan R
NRNandavardhan R
Nandavardhan R
AAAashishkumar
Aashishkumar
DGDivya Guru
Divya Guru
The advent of Large Language Models LLMs marks a milestone in Artificial Intelligence, altering how machines comprehend and generate human language. However, LLMs are vulnerable to malicious prompt injection attacks, where crafted inputs manipulate the models behavior in unintended ways, compromising system integrity and causing incorrect outcomes. Conventional detection methods rely on static, rule-based approaches, which often fail against sophisticated threats like abnormal token sequences and alias substitutions, leading to limited adaptability and higher rates of false positives and false negatives.This paper proposes a novel NLP based approach for prompt injection detection, emphasizing accuracy and optimization through a layered input screening process. In this framework, prompts are filtered through three distinct layers rule-based, ML classifier, and companion LLM before reaching the target model, thereby minimizing the risk of malicious interaction.Tests show the ML classifier achieves the highest accuracy among individual layers, yet the multi-layer framework enhances overall detection accuracy by reducing false negatives. Although this increases false positives, it minimizes the risk of overlooking genuine injected prompts, thus prioritizing security.This multi-layered detection approach highlights LLM vulnerabilities and provides a comprehensive framework for future research, promoting secure interactions between humans and AI systems.

8 August 2024 in Research Square
Verified
Preprint
Open access
PDF file
DGDivya Guru
Divya Guru
SPSupraja Perumal
Supraja Perumal
Decentralized energy trading stands as a significant avenue for enhancing the utilization of Sustainable Energy (SE) resources within the Grid network, while simultaneously mitigating losses associated with extensive grid infrastructure. Four distinct dual auction scheme, including Trade Reduction, McAfee, Vickrey Clarke Groves (VCG), and Average, aim to improve the efficiency of decentralized peer-to-peer energy exchange. This research work systematically assessed these mechanisms in a range of forms of microgrid (MG). Participants can specify how much they are willing to spend on various energy modules on varying period that incorporates user priority, bidding methods, and time of use tariffs. In most MG configurations, the Average and VCG processes were shown to be the most efficient. In particular, it was discovered that the average mechanism worked best for a market-focused MG, but the VCG mechanism was mostly beneficial for trading outside of peak hours. This work provides a thorough approach that skillfully determines and suggests the best auction procedures for various MG configurations and consumption schedules, opening the door for extra effective P2P energy exchange.