Offensive AI LabOffensive AI is the malicious use of artificial intelligence to power, automate, and scale cyberattacks, as well as attacks targeting AI systems themselves. It includes autonomous attack agents, AI-driven vulnerability discovery and exploitation, adaptive malware, deepfakes, and automated social engineering, alongside attacks on AI models and agents through prompt injection, adversarial machine learning, data poisoning, agent hijacking, tool misuse, and supply chain compromise.
The Offensive AI Lab (OAI Lab) studies how adversaries use AI to enhance their attacks and exploit AI systems. The objective of the lab is to protect society by improving AI safety and by identifying and mitigating AI threats before they become mainstream. We are located in the BGU Cyber Security Research Center in Be’er Sheva Israel.
Featured Research
Dedicated pages for selected projects from the lab, with papers, code, talks, and tools.
Our Supporters
The lab is supported by the Zuckerman STEM Leadership Program and by research grants from the organizations below. Thank you for your support!
Join Our Community
Join the Offensive AI Lab on Discord
Talk with our researchers and a growing community about AI security, AI agents, deepfakes, and our open-source tools.