adversarial examples

An NHS trust has confirmed a security incident in which adversarial perturbations were applied to medical images prior to processing by an AI-assisted diagnostic system, causing systematic misclassification in a radiology screening programme.

Recent research demonstrates that vision-language models including GPT-4V, Gemini Pro Vision, and open-source alternatives are highly susceptible to adversarial image perturbations, with attacks transferring across models at rates significantly higher than classical vision model attacks.