Pages

Selected papers

Research

My thesis on systems, security, and AI.

01

Characterising Indirect Prompt Injection in Retrieval-Augmented Generation Systems

My current paper on indirect prompt injection as a context-integrity problem, with a threat model, taxonomy, and evaluation framing for RAG systems.

02

LLM-Firewall: RAG Detection Middleware Architecture

Personal research on the RAG detection middleware architecture I designed to detect and sanitize IPI attacks in real-time.

03

LLM-Firewall: A Novel Taxonomy of IPI Attacks

A novel taxonomy of indirect prompt injection attacks in enterprise RAG systems.