Research
Work from the Data Science and Machine Learning research group at Sharif University, centered on AI Safety, LLM security, and NLP for low-resource languages.
The Sentinel’s Dilemma: Who Guards Our AI Guardians?
Unveiling BackdoorBench: A Critical Benchmark for AI Security
Overview In this project, we fine-tuned the Wav2Vec2 model to perform sentiment analysis based on both voice features and text transcripts from the Shemo dataset. This hybrid approach allows robust emotion recognition...
Overview In this project, we developed an Android application to estimate the location of cellular network cells using Received Signal Strength Indicator (RSSI) and GPS data. The application collects signal information and...
Overview In this project, we explore multimodal sentiment analysis, which involves analyzing both text and image data together. Our goal is to predict sentiment labels (positive or negative) based on combined information...
Project Iridium
My Internship at the NLP Lab :