TY - GEN
T1 - A Novel Poisoning Attack on Few-Shot based Network Intrusion Detection
AU - Alhussien, Nour
AU - Aleroud, Ahmed
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - With the advancement of Machine Learning (ML) algorithms, more organizations started using Machine Learning based Intrusion Detection Systems (ML-IDSs) to mitigate cyberattacks. However, the lack of training datasets is a major challenge when creating those systems. Therefore, using pre-trained models and small amount of labeled network data or few-shots from internal sources are possible solutions to overcome this challenge. However, using pretrained models or external datasets introduces the risk of poisoned machine learning models. This work investigates a novel poisoning attack that creates a diverse mini cluster of attacks and normal instances around an attack instance, then use the instances in that cluster to poison that instance. The poisoned instances are then injected into training data. A trained model is then created by projecting a labeled data from a poisoned source and the few labeled shots from the target organization. An anomaly-based intrusion detection model is utilized to examine the effectiveness of the introduced approach under the proposed poisoning attack. The results have shown that the attack is effective in the context of few-shot IDS learning.
AB - With the advancement of Machine Learning (ML) algorithms, more organizations started using Machine Learning based Intrusion Detection Systems (ML-IDSs) to mitigate cyberattacks. However, the lack of training datasets is a major challenge when creating those systems. Therefore, using pre-trained models and small amount of labeled network data or few-shots from internal sources are possible solutions to overcome this challenge. However, using pretrained models or external datasets introduces the risk of poisoned machine learning models. This work investigates a novel poisoning attack that creates a diverse mini cluster of attacks and normal instances around an attack instance, then use the instances in that cluster to poison that instance. The poisoned instances are then injected into training data. A trained model is then created by projecting a labeled data from a poisoned source and the few labeled shots from the target organization. An anomaly-based intrusion detection model is utilized to examine the effectiveness of the introduced approach under the proposed poisoning attack. The results have shown that the attack is effective in the context of few-shot IDS learning.
KW - Intrusion detection
KW - anomaly detection
KW - few-shot learning
KW - machine learning
KW - poisoning attacks
UR - http://www.scopus.com/inward/record.url?scp=85164733499&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85164733499&partnerID=8YFLogxK
U2 - 10.1109/NOMS56928.2023.10154453
DO - 10.1109/NOMS56928.2023.10154453
M3 - Conference contribution
AN - SCOPUS:85164733499
T3 - Proceedings of IEEE/IFIP Network Operations and Management Symposium 2023, NOMS 2023
BT - Proceedings of IEEE/IFIP Network Operations and Management Symposium 2023, NOMS 2023
A2 - Akkaya, Kemal
A2 - Festor, Olivier
A2 - Fung, Carol
A2 - Rahman, Mohammad Ashiqur
A2 - Granville, Lisandro Zambenedetti
A2 - dos Santos, Carlos Raniery Paula
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 36th IEEE/IFIP Network Operations and Management Symposium, NOMS 2023
Y2 - 8 May 2023 through 12 May 2023
ER -