New research shows that threat actors can easily implant backdoors in diffusion models used in DALL-E 2 and open-source text-to-image models.
View Article on VentureBeat
AI,Business,Security,AI, ML and Deep Learning,AI/ML models,backdoors,category-/Science/Engineering & Technology/Robotics,ChatGPT,DALL-E 2,Data Security and Privacy,deep learning,diffusion models,Generative AI,ML models,neural networks,Stable Diffusion
category-/Science/Engineering & Technology/Robotics