How Easily Can Adversarial Context Change Jev’s Decisions?
By Mohammad Karami, PhD
Read updateVlacia Blog
Latest updates
The Hidden Risk of Deploying Open-Source AI Models
By Mohammad Karami, PhD
Read updateHow a Git Patch Turned Into Remote Code Execution: Inside the Gitea CVE-2026-60004 Attack
By Mohammad Karami, PhD
Read updateJailbreaking Vision-Language Models
By Mohammad Karami, PhD
Read updateBackdoors Inside AI Models
By Mohammad Karami, PhD
Read updateAgent Security Bench
By Mohammad Karami, PhD
Read updateSafety concerns over vision-language AI models
By Mohammad Karami, PhD
Read updateEliciting Knowledge from LLMs
By Mohammad Karami, PhD
Read update