Research agenda

Research

My work sits at the intersection of autonomous systems, computer vision, and trustworthy machine learning. I study how perception fails, how those failures can be measured realistically, and how models can remain useful under attack and uncertainty.

Overview

I am a Postdoctoral Research Associate in the School of Computing at Clemson University and a member of TigerSec Lab, where I work with Prof. Mert D. Pesé on the security, robustness, and trustworthiness of autonomous-vehicle perception systems.

My research spans adversarial sensing, physical-world and black-box attacks, vision-language models for autonomous driving, robust 3D point-cloud perception, and dependable multimodal reasoning.

Previously, I was a Visiting Researcher at Carnegie Mellon University’s CyLab in 2023 and an Assistant Professor of Computer Science at Sirjan University of Technology from 2018 to 2022, where I also served as Department Chair.

Secure Autonomous Perception

Physical and black-box attacks, realistic evaluation, and defenses for camera- and LiDAR-based perception.

adversarial sensing · physical attacks · autonomous vehicles

Vision-Language Models for Driving

Robust multimodal reasoning, traffic-scene understanding, and test-time adaptation for driving systems.

vision-language models · multimodal reasoning · test-time adaptation

3D Vision and Point Clouds

Efficient methods for point-cloud recognition, segmentation, tracking, and geometric representation learning.

point clouds · 3D perception · geometric deep learning

Trustworthy Machine Learning

Reliability under distribution shift, uncertainty-aware deployment, and interpretable failure analysis.

robustness · uncertainty · explainability

Projects

Active research

Active

Resilient Autonomous Vehicle Perception Under Adversarial Settings

Research on realistic physical attacks and defenses for camera- and LiDAR-based autonomous-vehicle perception, with an emphasis on robustness under changing viewpoints, distance, and environmental conditions.

autonomous driving · adversarial perception · camera and LiDAR

Period: 2025–2026
Sponsor: U.S. DOT UTC TraCR
Role: Key Personnel