Institutional Repository

Browsing Theses and Dissertations by Author "Farhat, Hikmat, Ph.D."

Browsing Theses and Dissertations by Author "Farhat, Hikmat, Ph.D."

Sort by: Order: Results:

  • Geagea, Marybel (Notre Dame University-Louaize, 2019-05)
    The Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA) is a test used to differentiate between humans and machines. In this thesis, we have implemented a deep neural network architecture to automatically recognize CAPTCHAs. The main idea behind this thesis is to test the reliability of test-based CAPTCHAs in differentiating between humans and machines. We utilized convolutional neural networks instead of the conventional strategies of CAPTCHA breaking which, typically, use segmentation techniques. Our model is comprised of 8 layers to learn textbased images; ...
  • Salem, Elie (Notre Dame University-Louaize, 2006)
    A denial of service (DoS) attack is an attempt by a person or a group of persons to cripple an online service. This can have serious consequences on companies like Amazon and eBay, which rely on their online availability to do business. Many defense mechanisms have been proposed to thwart DoS attacks. One of these defense mechanisms is called hop-count filtering. Although an attacker can forge any field in the IP header, he or she cannot falsify the number of hops an IP packet takes to reach its destination. This hop-count information can be inferred from the time-to-live value in the IP header. ...
  • Younes, Ceaser (Notre Dame University-Louaize, 2014)
    Web services are form of middleware to exchange information between systems over a network. With the advent of the age of mobile devices and their diversity, the importance of web services became all the more apparent. Every web service grants certain functionality and can utilize other web services to gain more functionality and more robustness. Such a service that combines the functionality of other services is called a composite service and the process of designing such a service is called a composition. This thesis studies an on-the-fly algorithm that efficiently checks for the possibility ...
  • Rammouz, Veronica (Notre Dame University-Louaize, 2021)
    The internet has made room for lots of unwanted activity to propagate through computers. In response, many methods were established to detect a certain computer executable as malicious. However, there were still loopholes for hackers within traditional systems. Some methods use machine learning others use deep learning. There are some drawbacks to each method, such as reverse analysis and restricted simulation on different execution paths, as well as long execution time. Some methods cannot generalize well and cannot scale to large amounts of data. Moreover, anti-viruses, using signature-based ...

Search DSpace


Advanced Search

Browse

My Account