Freeborn HD

I’m a passionate AI Red Team Specialist with foundational cybersecurity knowledge and hands-on SOC exposure. I focus on reviewing prompts, validating AI-generated outputs, and testing LLM systems for safety, bias, and guideline compliance—especially where real-world adversarial behavior can slip through.

Since Jan 2025, I’ve been conducting prompt injection and AI vulnerability tests on public AI models, analyzing responses for bias, safety gaps, and information leakage. I document findings clearly and provide actionable recommendations to improve AI safety, and I also participate in AI bug bounty programs to identify exploitable weaknesses.

Through an SOC Analyst internship (basic knowledge), I monitored security events with SIEM tools, supported incident detection and triage, and assisted with vulnerability scans and reporting for senior analysts. Alongside this, I build structured LLM evaluation and AI workflow projects, test models like ChatGPT, Claude, and Gemini, and strengthen my practice with tools such as Lakera Gandalf, prompt testing environments, and security testing utilities.