whoami
Divya Rawat
Cybersecurity researcher with a focus on evolving attack surfaces in AI-driven systems. I approach security with an offensive mindset: identifying vulnerabilities, understanding how systems break, and exploring how emerging technologies like large language models introduce new classes of risk.
Background
My background is rooted in cybersecurity research, with hands-on experience in identifying vulnerabilities and analyzing real-world attack scenarios. Through work in areas like vulnerability research, auditing, and pentesting, I’ve developed a practical understanding of how systems are exploited.
Over time, my focus has shifted toward AI security, where traditional security assumptions no longer fully apply. I write about the security of AI systems: how they fail, how they’re exploited, and how they can be hardened. My focus spans adversarial examples, prompt injection, model poisoning, and the broader threat landscape that emerges when AI becomes infrastructure.
This blog is where I publish research notes, attack breakdowns, and commentary on the evolving AI security landscape.