Skip to content

MeghvShetty/ai-security-research

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

AI Security Research

Hands-on research at the intersection of offensive security and AI systems. This repo documents my practical work across LLM threat modelling, prompt injection testing, agentic AI attack surfaces, and AI red teaming techniques.

Active lab work from HTB Certified Offensive AI Expert (COAE) and independent research conducted alongside governance work in regulated financial services.


Research Areas

1. Prompt Injection & Jailbreaking

Techniques for direct and indirect prompt injection across LLM-integrated applications. Testing trust boundaries between user input, system prompts, and tool-calling behaviour in agentic systems.

2. RAG Pipeline Security

Attack surface analysis of Retrieval-Augmented Generation architectures — data poisoning via vector store manipulation, context window abuse, and embedding inversion techniques.

3. Agentic AI Threat Modelling

STRIDE-based threat models for multi-agent systems built on frameworks including Griptape and Google ADK. Focus on privilege escalation between agents, insecure tool use, and lateral movement via compromised context.

4. Model Extraction & Inference Attacks

Exploratory work on membership inference and model extraction via API interaction patterns.


Structure

  • /threat-models STRIDE threat models for common AI architectures
  • /prompt-injection PoC payloads and bypass techniques
  • /rag-attacks Vector store poisoning and retrieval manipulation
  • /agentic-systems Multi-agent attack surface research
  • /htb-labs Write-ups from HTB COAE modules (where permitted)

Certifications Driving This Work

  • HTB Certified Offensive AI Expert (COAE) — In Progress
  • ISO 42001 — AI Management Systems (PECB)

Methodology

Threat modelling follows STRIDE. Attack techniques are mapped to OWASP Top 10 for LLMs and MITRE ATLAS where applicable.

All research is conducted in controlled lab environments.


This repo grows as the research does. Follow for updates.

About

Hands-on AI security research — LLM threat models, prompt injection testing, and offensive AI techniques. Lab work from HTB COAE and beyond.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors