Are you interested in cybersecurity and privacy research? Do you want to work on cutting-edge research and cool projects? You have come to the right place; We have several open positions.

Please contact Dr. Takabi if you are interested in any of the positions.






PhD Position 1: Fully Funded PhD Position in Secure Privacy-preserving Deep Learning

Deep learning with neural networks has become a highly popular machine learning method due to recent breakthroughs in computer vision, speech recognition, and other areas. However, the deep learning algorithms requires access to raw data which is often privacy sensitive. On the other hand, deep learning systems can be fragile and easily fooled. For example, an attacker could add adversarial perturbations often invisible to human vision to an image to cause a deep neural network to misclassify the perturbed image. Such attacks go beyond image classification, and are effective across different neural network architectures and applications. This project investigates a novel combination of techniques enabling secure, privacy-preserving deep learning. Our approach employs a combination of homomorphic encryption, secure multi-party computation (SMC), differential privacy techniques to develop secure private deep learning algorithms to provide guaranteed privacy and provable security.

Related Publication:


PhD Position 2: Fully Funded PhD Position in Formal Cyber Deception

Cyber deception is a proactive technique to manipulate the mental state and cognitive thinking process of the adversary so that we can degrade and mitigate their attack effectiveness. It is essential to establish effective mental models for understanding and tracking the adversaries’ intent, capability, and decision process, and develop deception information formulation and communication techniques to provide a quantifiable measure on how a given deception approach will drive metal state change. This project aims to design and develop a scientific foundation for defensive deception by presenting a deception logic that models different dimensions of deception, and augmenting this modeling logic with necessary quantitative reasoning paradigms to generate coherent and affordable deception plans.

Related Publication: