Enhanced Prototypes of the Approach and Experimental Evaluation Based on a Classification Task for the Prevention of Training Poisoning Attacks

Abstract

Most recent studies have shown several vulnerabilities to attacks with the potential to jeopardize the integrity of the model, opening in a few recent years a new window of opportunity in terms of cybersecurity. The main interest of this thesis is directed towards data poisoning attacks involving label-flipping, this kind of attacks occur during the training phase, being the aim of the attacker to compromise the integrity of the targeted machine learning model by drastically reducing the overall accuracy of the model and/or achieving the missclassification of determined samples. This thesis is conducted with intention of proposing two new kinds of data poisoning attacks based on label-flipping, the targeted of the attack is represented by a variety of machine learning classifiers dedicated for malware detection using mobile exfiltration data. With that, the proposed attacks are proven to be model-agnostic, having successfully corrupted a wide variety of machine learning models; Logistic Regression, Decision Tree, Random Forest and KNN are some examples. The first attack is performs label-flipping actions randomly while the second attacks makes use of explainable artificial intelligence techniques to perform label flipping in only one of the classes. The effects of each attack are analyzed in further detail with special emphasis on the accuracy drop and the misclassification rate. Finally, this thesis pursuits further research direction by suggesting the development of a defense technique that could promise a feasible detection and/or mitigation mechanisms; such technique should be capable of conferring a certain level of robustness to a target model against potential attackers.

Date of Award	Dec 2022
Original language	American English