Diffusion models can be contaminated with backdoors, study finds

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.

ai backdoors business chatgpt dall-e 2 data security and privacy deep learning diffusion models engineering & technology generative ai ml and deep learning ml models neural networks research robotics science security stable diffusion study text threat threat actors