Security engineer and PhD researcher in adversarial machine learning. I break models to make them harder to break: red-teaming ML models, LLM agents, and RAG pipelines, and engineering the ML-driven detection that defends critical infrastructure against attackers who adapt.

• AutoMCP - CoAnalyst: a LangGraph research analyst for OT/IT alert triage with human review
• Agentarium - a local, read-only map of agent work, with project islands, mission boards, and evidence replay
• Watching an SSRF walk out of the sandbox - full writeup of CVE-2026-58196, host-side SSRF in an MCP runtime
• Doctoral research - evaluating and hardening ML-based intrusion detection against adaptive evasion; security of agentic LLM SOC analysts in OT networks
• Vulnerability research on AI-agent infrastructure: MCP servers, agent runtimes, coding assistants, disclosed responsibly
• Field notes - writeups land here as disclosures go public

AI red teaming : evasion, model extraction, data poisoning, prompt injection, robustness evaluation

Security engineering : ML-driven detection, SIEM, IDS (Suricata, Zeek), MITRE ATT&CK mapping

Critical infrastructure : OT/ICS protocols (Modbus, CAN, PROFINET), SCADA, fieldbus security

Vulnerability research : AI-agent infrastructure, exploitation, responsible disclosure

Certs : eJPTv2 • ISC2 CC (+ CC exam development volunteer) • NVIDIA Exploring Adversarial Machine Learning

Research collaboration, responsible disclosure, or an interesting target model: jaafer.rahmani@owasp.org