Vlacia Blog

Latest updates

August 16, 2026

Jailbreaking Vision-Language Models

By Mohammad Karami, PhD

August 11, 2026

Backdoors Inside AI Models

By Mohammad Karami, PhD

August 8, 2026

Agent Security Bench

By Mohammad Karami, PhD

August 6, 2026

Safety concerns over vision-language AI models

By Mohammad Karami, PhD

August 5, 2026

Eliciting Knowledge from LLMs

By Mohammad Karami, PhD