Re:AI Resistance: some recent anti-AI stuff that’s worth dis...
by bostik on Tuesday April 21, 2026 @12:36AM
(#47844574)
> unless you keep the poisoning attack strictly inaccessible to the public
This is likely impossible. As the in-vogue breed of model extraction methods ("distillation attacks") demonstrates, you can infer the underlying training and/or fine-tuning of a model with a series of carefully constructed prompts.
Another name of model poisoning? Adversarial fine-tuning.
This is likely impossible. As the in-vogue breed of model extraction methods ("distillation attacks") demonstrates, you can infer the underlying training and/or fine-tuning of a model with a series of carefully constructed prompts.
Another name of model poisoning? Adversarial fine-tuning.