Ahmet Aksoy | Aksoy Lab

Team:

		Ahmet Aksoy, Ph.D. Assistant Professor aksoy {at} ucmo.edu Computer Science & Cybersecurity University of Central Missouri
		Sachin Rana Automated Fast-flux Detection using Machine Learning and Genetic Algorithms sxr53490 {at} ucmo.edu
		Emiline Stewart Network Traffic Fingerprinting using Artificial Bee Colony Algorithm ers10570 {at} ucmo.edu
		Sharwin Reddy Network Traffic Fingerprinting using Ant Colony Algorithm sxp32460 {at} ucmo.edu
		Mohamed Louhaichi Various Incident Classification mxl73670 {at} ucmo.edu
		Swathi Moganti Network Traffic Fingerprinting Survey moganti {at} ucmo.edu
		Rohith Pandrala Host Fingerprinting using SSL rxp78250 {at} ucmo.edu
		Jayavardan Pasupuleti SILEA with Parameter Optimization jxp85060 {at} ucmo.edu
		Shravya Goli GA & Feature Selection algorithms comparison sxg46220 {at} ucmo.edu
		Anusha Telagamsetty Network Traffic Fingerprinting Survey axt94010 {at} ucmo.edu
		Sai Sohita Parimi Network Traffic Fingerprinting Survey sxp27740 {at} ucmo.edu

Research:

• Operating System Fingerprinting:

  Operating system (OS) fingerprinting is the process of remotely detecting the OS of a target device. One of the most important steps to maintain security of a network is to be aware of which software, such as the OS, is used within the network. Our research proposes a completely automated method to perform passive OS fingerprinting. We employ a genetic algorithm and machine learning algorithms in order to create a completely automated, non-expert based approach. Our tool is available at: OSID




• IoT Device Fingerprinting:

  IoT device fingerprinting is the process of remotely detecting the vendor and type of IoT devices. Our research proposes a completely automated IoT device classification that can identify the device type from a single packet. We employ a genetic algorithm and machine learning algorithms in order to create a completely automated, non-expert based approaches. Our tool is available at: SysID




• Fast-flux Detection:

  Our research proposes a completely automated fast-flux identification using a single packet. We employ a genetic algorithm and machine learning algorithms in order to create a completely automated, non-expert based approaches.