This lab exists in the Center for Criminal Justice, Intelligence and Cybersecurity with the primary purpose of conducting research and teaching in the area of security and privacy at State University of New York (SUNY) Canton.
The lab collaborates with faculty members nationally and internationally who are interested in the area of security and privacy.
The group consists of a number of intelligent, enthusiastic, and highly motivated students working on interesting state-of-the-art projects.
In this area of research, we try to identify valuable data of each individual, propose methods to protect them against malicious behaviors and attacks, and provide solutions to recover from attacks if the security is compromised. Once the valuable data is related to personal identifiable information, revealing those information is not only a security problem but a privacy concern. Privacy Enhancing Technologies (PET) can help us to identify sensitive information and propose solutions to introduce privacy-preserving models to protect data privacy of the individuals.
One of the recent research projects in this area is the detection of abnormal human activities. Imagine a student walking in a parking lot then suddenly collapses. Without anyone around or the personnel responsible for monitoring the CCTV cameras catching it, help will be nowhere to be found. The goal of the project is developing a system that would be able to detect such behavior and learn in due time. Furthermore, we are investigating the connection between detecting human behavior and privacy risks associated with that. Currently there is a challenge in efficiently anonymize the video streams and maintain the usability of the video.
We are currently working on entity resolution over incomplete data. Different data sources may contain the same data records refer to the same entity in the real-world, entity resolution is to find cluster these data records to the same group. Existing entity resolution methods are almost based on the complete data sources, but it is common that data sources contain incomplete data records. To improve the accuracy of entity resolution, it is necessary to explore ad-hoc ER method for incomplete data. Besides, We are also interested in the research work related to the queries over incomplete data sources.
In this area our project focuses on the use of natural language processing to analyze text messages in order to identify persons with psychological problems. The primary focus is to first design a corpus that would allow for identification of such texts and later come up with a machine learning model that would be able to identify psychological issues. The goal is to apply the model to come up with a location based model to identify an upsurge of areas with people suffering from psychological problems.
This research investigates users' behavior in terms of how they choose their privacy settings on Facebook. It examines the impact of faces and tags existence on users' privacy. By using face detection, tagging and their location on photos posted by individuals, a new method is proposed to measure behavior of privacy of the individuals. Moreover, we extend the work on YourPrivacyProtector. The application monitors privacy settings for users and screens the privacy risks in their profiles. It then educates social media users of privacy-related issues, helping users to avoid them when using social media networks. We use machine learning techniques to understand privacy settings of different users and recommend them a stronger setting.
In this project we work on children's privacy in social media services and intrusive apps with the objectives to create awareness for both users and developers, and eventually a guideline to truly understand what the real situation in today's online world is and how we can design tools and privacy policy to meet the needs of digital generation. The process involves collecting raw data from users, analyzing data and predicting future trends that can better protect users' privacy and security, especially young generation, in online platforms.
In this project, the goal is to study the effect of the human behavior and cognitive biases in the security and usability decision making. In the first stage, the users' decision-making toward security and usability had been studied through the mental model approach. To elicit and depict users' security and usability mental models, crowd sourcing techniques and a cognitive map method are applied and we have performed an experiment to evaluate our findings using Amazon MTurk. In the second stage, we will setup a controlled experiment to measure the cognitive load using eye tracking machine to explore if there is a correlation between the cognitive load and the cognitive biases that affect users' security decisions.
Wearable devices promise great influence on the quality of life, they also have distinctive capabilities of collecting users' sensitive information in real time. They can perform many of computing tasks that seen in laptops and mobile devices and tracking users' activities. It worth to have a privacy model that can effectively protect users' information. Our goal is to ensure users' privacy remains protected. We are currently working on a privacy model that provides a friendly user interface. The proposed UI helps users to set their privacy preferences and express themselves. In addition, we are working on an access control model that grants access to users' information based on their privacy preferences.
Lab Director
Research Innovation Fellow
Manufacturing Innovation Fellow
Criminal Justice Fellow
AI Faculty Member
Visiting Researcher, France
PhD Candidate
Cybersecurity student
CyberSecurity Student
CyberSecurity Student
CyberSecurity Student
CyberSecurity Student
CyberSecurity Student
CyberSecurity Student
CyberSecurity Student
CyberSecurity Student
| Garron Fawcett | Celeste Hall | Arjuman Sultana | Todd Mobley | Matthew Boehlke |
|---|---|---|---|---|
| Kristen Harris | Sravan Kumar | Peter Tenkku | Peter Grapentien | James Gross |
| Nathan Harper | Omar Alaql | David Christ | John Ponchak | Anthony Scott |
| Kyle McMaster | Isaac Park | David Figura | Timothy Strawbridge | Michael Garlak |
| Tahani Albalawi | Roba Darwish | Muhammad Mohzary | Anuj Vasil | Grant Myers (Brown University) |
| Aarushi Singh | Emil Shirima | Bryce Benjamin | Hanan Muhajeb | Karl Godard |
| Amanda Porter | Srikanth Tadisetty | David Selinger | Ken Messner | Paweena Manotipya |
| Betis Baheri | Joel Carbone | Dakota Smoke | Jared Durieux | Maryam Ghasemian |
| Jeanna Manning | Sean Scarnecchia | Blake Pecore | Alex Wolfe | Dylan Bradley |
| Dr. Weilong Ren | Dr. Bizhan Pijani | Isaak Babaev | Hailey LePage | Liam Szabo |
| Dr. Zhengyong Ren | Brandon Ferrotta | Kate Hughes | Jake Rabideau | Rob Germann |
| Anishka Mendez | Andrew Puehn | Kyle Meagher | Eamon Goodwin | Nate Mercier |
Our most recent publication can be found on here on Google Scholar.
Send us an email with your CV at ghazinourk@canton.edu
Advanced Information Security and Privacy Lab
Center for Criminal Justice, Intelligence and Cybersecurity, SUNY Canton
34 Cornell Dr, Canton, NY 13617
Tel: 315-386-7067
