International Journal For Multidisciplinary Research

E-ISSN: 2582-2160   •   Impact Factor: 9.24

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 7, Issue 1 (January-February 2025) Submit your research before last 3 days of February to publish your research paper in the issue of January-February.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 7 Issue 1
January-February 2025

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Secure Artificial Intelligence (SAI): A Dual-layer defence model against prompt injection and prompt poisoning attacks

Author(s) Hitika Teckani, Devansh Pandya, Harshita Makwana
Country India
Abstract Secure Artificial Intelligence (SAI): A Dual-layer defence model against prompt injection and prompt poisoning attacks.
Keywords— Large Language Model, Secure Artificial Intelligence, Artificial Intelligence, Prompt Injection, AI security.
Abstract— Artificial Intelligence (AI) is deeply embedded in sectors handling sensitive information and mission-critical operations, and safeguarding these systems has become paramount. This paper introduces a novel dual-layer defence system termed Secure Artificial Intelligence (SAI), designed to mitigate risks associated with prompt injections and prompt poisoning attacks. Using two Large Language Models (LLMs) in a sequential setup “SAI”– a “Guard” model for initial input prompt classification which effectively filters out adversarial inputs to protect the AI system and a primary response model that responds to the user’s queries. Through rigorous testing, SAI has shown resilience in preventing malicious prompts from compromising AI responses, thereby significantly advancing AI security. This paper thoroughly examines SAI’s architecture, methodology, and performance, addressing the growing demand for secure and adversarial-resistant AI systems.
Keywords Large Language Model, Secure Artificial Intelligence, Artificial Intelligence, Prompt Injection, AI security
Field Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In Volume 7, Issue 1, January-February 2025
Published On 2025-01-18
Cite This Secure Artificial Intelligence (SAI): A Dual-layer defence model against prompt injection and prompt poisoning attacks - Hitika Teckani, Devansh Pandya, Harshita Makwana - IJFMR Volume 7, Issue 1, January-February 2025. DOI 10.36948/ijfmr.2025.v07i01.35371
DOI https://doi.org/10.36948/ijfmr.2025.v07i01.35371
Short DOI https://doi.org/g82gnz
View / Download PDF File

Share this



E-ISSN 2582-2160
CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 1Cover Page Vol 6 Isu 6Cover Page Vol 6 Isu 5

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About IJFMR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9687-828-838 editor@ijfmr.com