Multi-model assurance analysis showing large language models are highly vulnerable to adversarial hallucination attacks during clinical decision support
Mahmud Omar, Vera Sorin, Jeremy D. Collins, David Reich, Robert Freeman, Nicholas Gavin, Alexander W. Charney, Lisa Stump, Nicola Luigi Bragazzi, Girish N. Nadkarni, Eyal KlangQ12 Agustus 2025Afiliasi: DE, US