AppCon: Mitigating Evasion Attacks to ML Cyber Detectors

Adversarial attacks represent a critical issue that prevents the reliable integration of machine learning methods into cyber defense systems. Past work has shown that even proficient detectors are highly affected just by small perturbations to malicious samples, and that existing countermeasures are...

Full description

Saved in:
Bibliographic Details
Published in:Symmetry (Basel) 2020-04, Vol.12 (4), p.653
Main Authors: Apruzzese, Giovanni, Andreolini, Mauro, Marchetti, Mirco, Colacino, Vincenzo Giuseppe, Russo, Giacomo
Format: Article
Language:English
Subjects:
adversarial attacks
Algorithms
Computer simulation
cyber security
Cybersecurity
Datasets
Deep learning
Detectors
evasion attacks
Intrusion
Machine learning
Malware
network intrusion detection
Neural networks
Performance degradation
Poisoning
Sensors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Adversarial attacks represent a critical issue that prevents the reliable integration of machine learning methods into cyber defense systems. Past work has shown that even proficient detectors are highly affected just by small perturbations to malicious samples, and that existing countermeasures are immature. We address this problem by presenting AppCon, an original approach to harden intrusion detectors against adversarial evasion attacks. Our proposal leverages the integration of ensemble learning to realistic network environments, by combining layers of detectors devoted to monitor the behavior of the applications employed by the organization. Our proposal is validated through extensive experiments performed in heterogeneous network settings simulating botnet detection scenarios, and consider detectors based on distinct machine- and deep-learning algorithms. The results demonstrate the effectiveness of AppCon in mitigating the dangerous threat of adversarial attacks in over 75% of the considered evasion attempts, while not being affected by the limitations of existing countermeasures, such as performance degradation in non-adversarial settings. For these reasons, our proposal represents a valuable contribution to the development of more secure cyber defense platforms.
ISSN:2073-8994
2073-8994
DOI:10.3390/sym12040653