Research Assistant at RIML Lab
Date:
During my time as a Research Assistant at the Robust and Interpretable Machine Learning Lab under the supervision of Dr. Mohammad Hossein Rohban, I focused on advancing machine learning robustness and interpretability. My initial work involved conducting literature reviews and experiments on out-of-distribution (OOD) detection, particularly addressing spurious correlations. I tested various OOD benchmarks on spurious samples, analyzed the limitations of existing methods, and proposed improvements. This phase of research significantly contributed to understanding the complexities of OOD detection in real-world applications.
Building on this foundation, I worked on detecting backdoor attacks in machine learning models. This project led to the development of a novel detection method, which was accepted at NeurIPS 2024. I also designed a novelty detection method that is robust to style shifts in data distributions by distinguishing core from style features using a teacher-student framework. This research culminated in another paper submission to ICLR 2025, further showcasing my contributions to ensuring more secure and reliable AI systems.