Researching AI Safety, one rigorous step at a time.
I am a researcher focused on AI Safety, Trustworthy AI, and Large Language Models (LLMs). I graduated with a Bachelor's degree from Iran University of Science and Technology (IUST) and am currently pursuing a Master's degree in Computer Engineering at Sharif University of Technology.
Where I spend my time
AI Safety & Trustworthy AI
Defending large language models against backdoor attacks and securing neural architectures through comprehensive benchmarking (BackdoorBench, FTT-NAS).
NLP for Low-Resource Languages
Building Persian NLP infrastructure (DadmaTools v2) and affective-computing applications for underserved languages.
Applied Healthcare AI
DentalMind applies trustworthy-AI principles to a real clinical workflow, designed to support rather than replace a clinician's judgment.
Teaching
Teaching Assistant for Stochastic Processes and Machine Learning at Sharif, and for NLP, AI, and Theory of Languages at IUST.
DentalMind
Applying trustworthy-AI principles to a real clinical workflow — per-tooth dental radiograph analysis designed to support, not replace, a clinician's judgment. The flagship proof point of my healthcare-AI research focus.
View project →Milestones so far
Let's build something together.
Open to research collaborations and interesting problems. Reach out anytime.
amireza.vishteh@gmail.com