Dr. Nina Volkov 🇺🇸
CinderSec
LLM Security Researcher
Keynote: Jailbreaks & Defenses: Lessons from LLM Red-Teaming
Isolation patterns, layered filters, continuous evaluation.
Dr. Nina Volkov is an LLM Security Researcher at CinderSec, where she leads research into the vulnerabilities, risks, and defensive strategies surrounding large language models, with a focus on adversarial attacks, prompt injection, model exploitation, and safe deployment practices. With over a decade of experience spanning cybersecurity and machine learning, Dr. Volkov has built a reputation for uncovering critical security flaws in AI systems and translating complex technical risks into actionable guidance for engineering and policy teams alike, having previously worked on offensive security research and red-teaming efforts at leading technology and security firms. At CinderSec, she has been instrumental in developing frameworks for evaluating LLM robustness, identifying novel attack vectors such as jailbreaks and data exfiltration techniques, and advising organizations on building resilient, trustworthy AI systems. Dr. Volkov holds a Ph.D. in Computer Science with a specialization in Machine Learning Security from a leading research university, and her work reflects a deep commitment to ensuring that AI systems are deployed safely and responsibly in high-stakes environments. She is a frequent speaker at security and AI conferences, and continues to shape CinderSec's mission of securing the next generation of AI-powered systems against emerging threats.
