Content by Mark Russinovich, Giorgio Severi, Blake Bullwinkel, Yanan Cai, Keegan Hines and Ahmed Salem (1)
Mark Russinovich, Giorgio Severi, Blake Bullwinkel, Yanan Cai, Keegan Hines, and Ahmed Salem investigate how quickly the safety alignment of modern language and diffusion models can be compromised, revealing the fragility of current defense approaches.
End of content