P01
Advanced Prompt Injection Techniques in Modern RAG Systems
Detailed study in progress — taxonomy, attacks, defenses. Stay tuned.
Security & AI
research.
I study the intersection of AI systems and cybersecurity — how language models break under adversarial pressure, how retrieval pipelines leak sensitive data, and how to build defences that hold under real-world conditions. Practitioner research: everything is tested in live environments.
Research statement
"The rapid deployment of large language models in production systems has outpaced our understanding of their failure modes. My research focuses on characterising these failures systematically — and on building practical mitigations that don't require retraining the model."
LLM SecurityPrompt InjectionRAGAdversarial MLSIEMCVE ResearchRed Teaming
Research areas
01
LLM Security
Adversarial prompts, jailbreaks, prompt injection and model extraction in production systems.
02
RAG Architecture
Chunking strategies, hybrid search, eval frameworks and data poisoning in retrieval pipelines.
03
Threat Intelligence
Malware analysis, ATT&CK TTP mapping, SIEM automation and incident response workflows.
04
Secure AI Systems
Privacy-preserving inference, federated learning safeguards and ML supply chain risks.
Research
Papers & Preprints
Academic and technical writing on LLM security, RAG systems and AI red teaming — most works are currently in preparation or under submission.
P02
Production-grade RAG Evaluation at Scale
Framework + tooling for continuous RAG quality monitoring. Coming soon.
P03
ML-based Anomaly Detection in Enterprise SIEM
Rework in progress for public release.
Security Research
Vulnerability Disclosures
Responsible disclosure activity in AI/ML components — full CVE write-ups will be published after coordination completes.
CVE-20XX-XXXXXTBAMultiple prompt injection vectors (details soon)
Several responsible disclosures in progress — full write-ups coming after coordination.
Full advisory → coming after disclosure coordination
CVE-20XX-YYYYYTBADeserialization & injection issues in AI inference pipeline
Patched internally — public advisory planned after coordination completes.
Full advisory → coming after disclosure coordination
Speaking & Workshops
Talks & Lectures
Conference talks, workshops and guest lectures on AI security — upcoming events and slides will appear here when confirmed.
2025
Defending Modern LLM Applications
Talk · 45 min
Details will appear here once confirmed.
Details & slides → coming soon
2025
Practical AI Red Teaming Workshop
Workshop · 3h
Hands-on session planned — stay tuned.
Details & slides → coming soon
2024
OWASP LLM Top 10 – Practitioner View
Talk · 30 min
Updated version in preparation for public events.
Details & slides → coming soon
Want to collaborate on research
or review early drafts?
Get in touch
Got something
complex to build?
Full-stack products, AI integrations, security reviews — or anything that sits at the intersection. Reply within 24 hours.