Syed Yunas

Papers

Total Citations

H-Index

About

Syed Yunas is a researcher at the forefront of deep learning security, with a particular focus on adversarial machine learning and its real-world implications for intelligent systems. His most cited work, "Adversarial Detection: Attacking Object Detection in Real Time" (2023), makes a critical contribution by exposing the vulnerability of object detection models used in autonomous robots and surveillance systems. While prior research largely targeted static images or offline videos, Yunas demonstrates how these models can be compromised in real-time, dynamic environments—a significant leap in understanding the practical threats facing deployed AI. His findings have direct implications for the safety and robustness of self-driving cars, drones, and other perception-driven technologies. With 5 citations already, this work is gaining traction as a foundational reference in the emerging field of real-time adversarial attacks. Yunas’s research bridges the gap between theoretical adversarial examples and operational security, marking him as a rising voice in trustworthy AI. His work challenges the community to rethink how we secure perception systems against adaptive, real-world adversaries.