Skip to content

Graduate Research

• Accepted and Under Review Papers

GPS-IDS: An Anomaly-based GPS Spoofing Attack Detection Framework for Autonomous Vehicles

IEEE Transactions on Dependable and Secure Computing (Under Review)

Figure: GPS spoofing attack performed on real autonomous vehicle testbed called the ACL-Rover. Screenshots of the ground control station software during real-time data collection are presented.

In this paper, I developed a software algorithm framework to detect navigation anomalies and GPS spoofing attacks against the navigation system of an autonomous vehicle. The paper introduces GPS-IDS, a novel Intrusion Detection approach based on “Anomaly Behavior Analysis”. In an Anomaly Behavior Analysis approach, the normal behavior of a system is modeled, and any behavior outside the normal model is detected as an attack. One of the main contributions of this paper is to develop a normal behavior model of an autonomous vehicle that can predict the dynamic vehicle states accurately. To achieve this, I developed a physics-based autonomous vehicle normal behavior model by taking into account vehicle dynamics, state estimates, motion planning, and control algorithms with full mathematical support. The accuracy of this model has been validated by real-world vehicular data using autonomous vehicle testbeds. I used a combination of the developed autonomous vehicle behavior model and machine learning to identify anomalous data from the normal during GPS-guided autonomous driving. From my experiments, I created an extensive autonomous vehicle research dataset family, which is available on GitHub:

An Anomaly Behavior Analysis Framework for Securing Autonomous Vehicle Perception

IEEE/ACS International Conference on Computer Systems and Applications (IEEE AICCSA 2023), Egypt. (In press)

This paper proposes an Anomaly Behavior Analysis approach to detect a perception sensor attack against an autonomous vehicle. The framework relies on temporal features extracted from a physics-based autonomous vehicle behavior model to capture the normal behavior of vehicular perception in autonomous driving. By employing a combination of model-based techniques and machine learning algorithms, the proposed framework distinguishes between normal and abnormal vehicular perception behavior. To demonstrate the application of the framework in practice, we performed a depth camera attack experiment on an autonomous vehicle testbed and generated an extensive dataset. We validated the effectiveness of the proposed framework using this real-world data and released the dataset for public access. To our knowledge, this dataset is the first of its kind and will serve as a valuable resource for the research community in evaluating their intrusion detection techniques effectively.

• Posters and Projects

Intrusion Detection in Autonomous and Unmanned Vehicles in indoor and GPS-denied Environments

Poster Presented in NSF Center of Cloud and Autonomic Computing’s (CAC) Semi-annual Meeting at the University of North Texas, USA (November 2022)

This poster presents my research on Autonomous and Unmanned Vehicle security in indoor or GPS-denied environments. Such kind of indoor attacks can be LiDAR Spoofing or Vision Camera Blinding attacks. I have demonstrated how I was able to perform a LiDAR spoofing attack on QCcar Self-driving vehicle testbed. I am working on replicating the LiDAR Spoofing attack demonstrated by Y. Cao et al. in “Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving”. My goal is to come up with a LiDAR attack detection and protection system using Machine Learning and Multi-sensor Fusion (Camera-LiDAR-GPS fusion).

ACL-Rover: A testbed to Study GPS Security for Unmanned and Autonomous Vehicles

Global Positioning System (GPS), one of the most popular and relied Global Navigation Satellite Systems (GNSSs) is used by millions of Unmanned and Autonomous Vehicle for outdoor navigation. Civilian GPS being unencrypted, is always an easy attack surface for intruders to attack any autonomous system. Recently, Machine Learning based GPS Intrusion Detection Systems have grown popularity due to their high attack detection accuracy and effectiveness…

Undergraduate Research

• Published Conference Papers

Design and Development of a Biologically Inspired Robotic Cat for Research and Education

30th International Conference on Computer Theory and Applications (ICCTA 2020), Arab Academy for Science, Technology & Maritime Transport (AASTMT), Alexandria, Egypt (Published)

Biologically Inspired Robots are one of the most emerging technologies in robotics field where engineering knowledge can be used in biological systems to generate new hypothesis of different research. In this paper, we present a biologically inspired robotic cat for both experts and non-experts to use as a learning platform as well as to keep as a pet…

An Autonomous Delivery Robot to Prevent the Spread of Coronavirus in Product Delivery System

Due to the coronavirus situation around the world, safe and contactless home delivery services have become substantial concerns for the people while they are forced to stay at home. In this context, we have proposed a prototype robot that can be very helpful to reduce the risk of infectious disease transmission in the product delivery system during the extreme strain on healthcare and hygiene…

Effect of Channel Length and Dielectric Constant on Carbon Nanotube FET to Evaluate the Device Performance

Carbon Nanotube is one of the most emerging technologies for the development and growth of nano-scaled transistors. This paper deals with the impact of channel length and dielectric constant on Carbon Nanotube Field Effect Transistor (CNT-FET) in order to evaluate the device performance. The effect of dielectric constant has been deeply investigated in the work…

Comparative Analysis of a Bifacial and a Polycrystalline Solar Cell Device Perfomances By Optimizing Effective Parameters Using PC1D

As a source of clean energy, solar cells have become a prominent topic of research in recent years to achieve its most favorable efficiency at a low fabrication cost. In this paper, by using PC1D simulation software we have investigated the comparisons of the device performances and power conversion efficiencies between two types of silicon solar cells: bifacial solar cell and poly crystalline solar cell respectively. The main objective…

Layer thickness effect on power conversion efficiency of a P3HT:PCBM based organic solar cell

1st International Conference on Advances in Science, Engineering and Robotics Technology ICASERT 2019 (Published)

In recent years Organic Solar Cells have become a prominent topic of research to achieve an optimum efficiency at low cost. By using the GPVDM software on this paper, we have analyzed the effect on power conversion efficiency, changing simultaneously both the polymers and blending layer thickness of P3HT:PCBM based solar cell. Our main goal is to find which layer change keeps the power conversion efficiency output better. After comparing them, the result shows that setting the active layer (P3HT:PCBM) in an optimum fixed value and varying the polymer layer (PEDOT:PSS) gives a better output of PCE. In our paper, from the data in  both  cases, The highest efficiency is 4.50 percent where  P3HT:PCBM layer thickness is 2.2×10-7 m and PEDOT:PSS layer thickness is 1×10-7 m.