Research artifacts, open-source systems, and security testing frameworks from my recent work.
Excalibur is a difficulty-aware LLM agent design for real-world penetration testing. It couples typed tooling, retrieval-augmented security knowledge, task difficulty assessment, and evidence-guided attack tree search to reduce planning failures in multi-step penetration testing tasks.
Safety Snowball Agent is an agent-based framework for evaluating how safe visual inputs can combine into unsafe behavior in large vision-language models. The framework accompanies the NeurIPS 2025 paper “Safe + Safe = Unsafe?” and probes a multimodal jailbreak mechanism that differs from traditional adversarial-image attacks.
MASTERKEY is a research framework for automated jailbreak attack generation and defense evaluation for LLM chatbots. The framework supports systematic analysis of jailbreak strategies across commercial chatbot systems and was published at NDSS 2024.
PANDORA studies jailbreak attacks against retrieval-augmented generation systems through retrieval database poisoning. The work received the Distinguished Paper Award at AISCC 2024 and highlights a practical attack surface in RAG-enhanced LLM deployments.
NAUTILUS is an automated RESTful API vulnerability detection framework published at USENIX Security 2023. It combines API specification analysis with dynamic testing to uncover security flaws in modern web services.