Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning 2020
DOI: 10.1145/3395352.3402618
|View full text |Cite
|
Sign up to set email alerts
|

Generative adversarial attacks against intrusion detection systems using active learning

Abstract: Intrusion Detection Systems (IDS) are increasingly adopting machine learning (ML)-based approaches to detect threats in computer networks due to their ability to learn underlying threat patterns/features. However, ML-based models are susceptible to adversarial attacks, attacks wherein slight perturbations of the input features, cause misclassifications. We propose a method that uses active learning and generative adversarial networks to evaluate the threat of adversarial attacks on ML-based IDS. Existing adver… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
18
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
3
1
1

Relationship

0
10

Authors

Journals

citations
Cited by 42 publications
(18 citation statements)
references
References 22 publications
0
18
0
Order By: Relevance
“…Problems of labelling data and retraining systems provide an impetus to explore unsupervised and active learning. Unfortunately adversarial attacks are possible on active learning systems [146]. Lin et al [76] describe an enchanting attack to lure a machine learning system to a target state through crafting a series of adversarial examples.…”
Section: Takeawaysmentioning
confidence: 99%
“…Problems of labelling data and retraining systems provide an impetus to explore unsupervised and active learning. Unfortunately adversarial attacks are possible on active learning systems [146]. Lin et al [76] describe an enchanting attack to lure a machine learning system to a target state through crafting a series of adversarial examples.…”
Section: Takeawaysmentioning
confidence: 99%
“…Shu et al [30] introduced the Generative Adversarial Active Learning (Gen-AAL) algorithm that utilizes GANs with active learning to craft adversarial attacks against black-box MLbased NIDS. It requires a limited number of queries to the targeted model for labeled instances to train the GANs and does not demand a large training dataset.…”
Section: A Generation Of Aes To Attack Ml-based Nids Modelsmentioning
confidence: 99%
“…After only 400 epochs, they were able to reduce the traffic blocking percentage to zero. Similarly, in [119], the authors used a GAN with active learning to generate successful adversarial traffic with minimal training labels.…”
Section: Evasion Techniquesmentioning
confidence: 99%