Reliable Feature Selection for Adversarially Robust Cyber-Attack Detection
This work addresses cybersecurity threats by enhancing the reliability of ML-based detection systems in enterprise networks, though it appears incremental as it builds on existing feature selection and adversarial training methods.
The paper tackled the problem of improving adversarial robustness in ML models for cyber-attack detection by selecting reliable features and using adversarial training, resulting in significantly improved robustness without compromising generalization or increasing false alarms.
The growing cybersecurity threats make it essential to use high-quality data to train Machine Learning (ML) models for network traffic analysis, without noisy or missing data. By selecting the most relevant features for cyber-attack detection, it is possible to improve both the robustness and computational efficiency of the models used in a cybersecurity system. This work presents a feature selection and consensus process that combines multiple methods and applies them to several network datasets. Two different feature sets were selected and were used to train multiple ML models with regular and adversarial training. Finally, an adversarial evasion robustness benchmark was performed to analyze the reliability of the different feature sets and their impact on the susceptibility of the models to adversarial examples. By using an improved dataset with more data diversity, selecting the best time-related features and a more specific feature set, and performing adversarial training, the ML models were able to achieve a better adversarially robust generalization. The robustness of the models was significantly improved without their generalization to regular traffic flows being affected, without increases of false alarms, and without requiring too many computational resources, which enables a reliable detection of suspicious activity and perturbed traffic flows in enterprise computer networks.