بعد أكاديمية كاوست
As of October 2026, Nawaf is studying software engineering at King Saud University. Nawaf worked as an AI research intern at the HIVE Lab at the University of Toronto, where the team won the Best Poster Award, and presented the work at the KAUST Academy closing ceremony.
المشروع الصيفي
تخصص الذكاء الاصطناعي · دفعة 2026
Mechanistic Analysis of Template-Injection Jailbreaks in Diffusion Language Models
Our project investigates how jailbreak attacks affect diffusion language models in healthcare. We study whether unsafe template injections leave detectable internal signatures and whether these signals can be used to steer the model back toward safer responses. Our findings show that harmful injections can be detected reliably, but correcting the resulting behavior remains more challenging.
مع أكاديمية كاوست
- دفعة 2026
جامعة تورنتو · البرنامج الصيفي للذكاء الاصطناعي
هل تريد تحديث بياناتك أو حذفها؟ تواصل معنا.