The Detection of a Ransomware attack on IoT devices Deployed on Cloud Computing Environment Using Artificial Intelligence and Machine Learning
PhD Candidate Temechu Zewdie
By: Temechu Zewdie
PhD advisor: Dr. Girma Anteneh
Tuesday, December 13, 2022 at 10:00 AM
PhD Committee
Dr. Girma Anteneh PhD Advisor, UDC
Dr. Paul Cotae Committee Chair, UDC
Dr.Thabet Kacem Member UDC
Dr. Dian Igoche, External Member from Robert Morris University
Dr. Tessema Guebre Xabiher External Member from National Scientific Foundation
Research Presentation
Cybersecurity is turning into a social phenomenon. Investors’ interest, public pressure, employee demands, and governmental regulations are strengthening the incentives for organizations to track and report cybersecurity goals and metrics within their environmental, social, and governance efforts as a business requirement. Traditional cybersecurity efforts that focus exclusively on awareness are failing to facilitate secure behavior and have led to loss of control amid an increasingly distributed ecosystem. The increasing number of cyber-attacks with the emergence of new technologies, such as cloud computing, artificial intelligence (AI), Internet of Thigs (IoT), and smart devices have been a big factors driving the urgency of having a better cybersecurity solution. Among those leading cyber-attacks, ransomware attack is found to be at the forefront. The rise of ransomware over the past few years is an ever-growing problem that has quickly become an extremely lucrative criminal enterprise. Targeted organizations often believe that paying the ransom is the most cost-effective way to get their data back — and, unfortunately, this may also be the reality. Ransomware employs the idea of crypto virology, which uses cryptography to design malware. The goal of ransomware is to extort ransom by threatening the victim with the destruction of their data. Despite numerous cybersecurity precautions, governments and businesses take various measures to combat ransomware attacks.
Cybersecurity refers to technology and practices aimed at protecting networks and information from damage or unauthorized access. Cybersecurity is vital because governments, companies and military organizations collect, process, and store a lot of information on computers. Most cybersecurity solutions use a rule – based or signature methodology that requires too much human intervention and institutional knowledge. Artificial intelligence may increase the productivity of human beings in order to increase the time spent on cybersecurity. AI can also benefit cybersecurity with automated techniques to generate whenever cyber threats are detected. AI is able to analyze massive amounts of data and allow the development of existing systems and software in an appropriate way to reduce cyber-attacks.
Thus, detecting ransomware has become an important undertaking involving various sophisticated AI/ML solutions for improving security. To further enhance ransomware detection capabilities, this research paper will address the ransomware attack cybersecurity issues using state-of-the art solution approach and applying AI – Machine Learning techniques to design and develop a better AI machine learning (AI/ML) model using Random Forest that helps to classify and detect IoT-based ransomware attacks whether benign or ransomware, in a cloud computing environment, and enhance the existing solution and ensures the detection of a ransomware attack on IoT devices deployed on a cloud computing environment to secure data. Moreover, our research will present different statistical results generated from the security analysis, classification, and detection of IoT-based ransomware attacks on a cloud computing environment by describing how AI-ML Algorithms can be further implemented with existing multilayer security solutions to protect vital data from ransomware attacks. Finally, we will display and prove how our research approach close the existing security gap and significantly mitigate the risk by showing a comparative analysis with another prior and current related research works.
Webex Link
Hosted by Cotae, Paul
https://universityofdc.webex.com/universityofdc/j.php?MTID=m78fe95f73b727627cfb2f465d3fad2b4
Tuesday, Dec 13, 2022 10:00 am | 3 hours | (UTC-05:00) Eastern Time (US & Canada)
Meeting number: 2634 842 6104
Password: M2uuV5KE4mH
Join by video system
Dial 26348426104@universityofdc.webex.com
You can also dial 173.243.2.68 and enter your meeting number.
Join by phone
+1-415-655-0003 United States Toll
Access code: 263 484 26104