Is this project an undergraduate, graduate, or faculty project?
Undergraduate
Project Type
individual
Campus
Daytona Beach
Authors' Class Standing
Siri Siqveland, Junior
Lead Presenter's Name
Siri Siqveland
Lead Presenter's College
DB College of Engineering
Faculty Mentor Name
Dr. Omar Ochoa
Abstract
In the modern age of computers and interconnected networks, cybersecurity and cyber-attackers are evolving in tandem to exploit each other’s vulnerabilities. One technique used by both parties is Operating System Fingerprinting (OSF): with the knowledge of what Operating System a target system is running, innate vulnerabilities can be identified and patched or exploited. Historically, OSF utilizes two main methods: passive and active—the former trades accuracy with undetectability while the latter is generally more detectable but more accurate. However, recent work has combined OSF with Machine Learning (ML) to improve accurate identification. The work presented here is a survey for the applications of ML on OSF for both active and passive methods and discusses how ML methods compare to the traditional non-ML methods. Various ML techniques are discussed in terms of their applications and accuracy, e.g., K Nearest Neighbor, Decision Trees, and Support Vector Machines. New tools have also been developed that apply ML to OSF, and the accuracy and methods of these tools are also detailed. The data compiled in this survey are then used to determine gaps in the research and possible direction for future work.
Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?
No
Included in
Artificial Intelligence and Robotics Commons, Cybersecurity Commons, Information Security Commons
A Survey on Machine Learning Applications for Operating System Fingerprinting
In the modern age of computers and interconnected networks, cybersecurity and cyber-attackers are evolving in tandem to exploit each other’s vulnerabilities. One technique used by both parties is Operating System Fingerprinting (OSF): with the knowledge of what Operating System a target system is running, innate vulnerabilities can be identified and patched or exploited. Historically, OSF utilizes two main methods: passive and active—the former trades accuracy with undetectability while the latter is generally more detectable but more accurate. However, recent work has combined OSF with Machine Learning (ML) to improve accurate identification. The work presented here is a survey for the applications of ML on OSF for both active and passive methods and discusses how ML methods compare to the traditional non-ML methods. Various ML techniques are discussed in terms of their applications and accuracy, e.g., K Nearest Neighbor, Decision Trees, and Support Vector Machines. New tools have also been developed that apply ML to OSF, and the accuracy and methods of these tools are also detailed. The data compiled in this survey are then used to determine gaps in the research and possible direction for future work.