Offensive AI Lab | We investigate how adversaries are using and abusing AI to perform malicious tasks (deepfakes, defense evasion, attack automation, and so on). Our goal is to identify and prevent these emerging threats before they become mainstream.

我们正在研究对手如何利用和滥用人工智能来执行恶意任务（例如，深度伪造、规避防御、攻击自动化等）。我们的目标是在这些新兴威胁成为主流之前，识别并阻止它们。