"In #BadDiffusion attack, a malicious actor modifies the training data and the diffusion steps to make the model sensitive to a hidden trigger. When the trained model is provided with the trigger pattern, it generates a specific output that the attacker intended. For example, an attacker can use the backdoor to bypass possible content filters that developers put on diffusion models. "

#DiffusionModels can be contaminated with #backdoors, study finds | #AI #AISecurity
https://venturebeat.com/ai/diffusion-models-can-be-contaminated-with-backdoors-study-finds/