Andrew McCarthy's Outputs (5)

Methods for improving robustness against adversarial machine learning attacks (2023)
Thesis

Machine learning systems can improve the efficiency of real-world tasks, including in the cyber security domain; however, these models are susceptible to adversarial attacks; indeed, an arms race exists between adversaries and defenders. The benefits... Read More about Methods for improving robustness against adversarial machine learning attacks.

Defending against adversarial machine learning attacks using hierarchical learning: A case study on network traffic attack classification (2022)
Journal Article

Machine learning is key for automated detection of malicious network activity to ensure that computer networks and organizations are protected against cyber security attacks. Recently, there has been growing interest in the domain of adversarial mach... Read More about Defending against adversarial machine learning attacks using hierarchical learning: A case study on network traffic attack classification.

Functionality-preserving adversarial machine learning for robust classification in cybersecurity and intrusion detection domains: A survey (2022)
Journal Article

Machine learning has become widely adopted as a strategy for dealing with a variety of cybersecurity issues, ranging from insider threat detection to intrusion and malware detection. However, by their very nature, machine learning systems can introdu... Read More about Functionality-preserving adversarial machine learning for robust classification in cybersecurity and intrusion detection domains: A survey.

Shouting through letterboxes: A study on attack susceptibility of voice assistants (2020)
Presentation / Conference Contribution

Voice assistants such as Amazon Echo and Google Home have become increasingly popular for many home users, for home automation, entertainment, and convenience. These devices process speech commands from a user to execute some action, such as playing... Read More about Shouting through letterboxes: A study on attack susceptibility of voice assistants.

Feature vulnerability and robustness assessment against adversarial machine learning attacks
Presentation / Conference Contribution

Whilst machine learning has been widely adopted for various domains, it is important to consider how such techniques may be susceptible to malicious users through adversarial attacks. Given a trained classifier, a malicious attack may attempt to craf... Read More about Feature vulnerability and robustness assessment against adversarial machine learning attacks.