Ben Ramsey on Nostr: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models “We introduce ...
Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
“We introduce Nightshade, an optimized prompt-specific poisoning attack where poison samples look visually identical to benign images with matching text prompts. Nightshade poison samples are also optimized for potency and can corrupt an Stable Diffusion SDXL prompt in <100 poison samples.”
https://arxiv.org/abs/2310.13828
“We introduce Nightshade, an optimized prompt-specific poisoning attack where poison samples look visually identical to benign images with matching text prompts. Nightshade poison samples are also optimized for potency and can corrupt an Stable Diffusion SDXL prompt in <100 poison samples.”
https://arxiv.org/abs/2310.13828