Adversarial Machine Learning in Network Intrusion Detection Systems

Alhajjar, Elie; Maxwell, Paul; Bastian, Nathaniel D.

doi:10.48550/arxiv.2004.11898

Cited by 5 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alhajjar et al [2] explore the use of evolutionary computations and generative adversarial networks as a tool for crafting adversarial examples that aim to evade machine learning models used for network traic classiication. These strategies were applied to the NSL-KDD and UNSW-NB15 datasets.…”

Section: Related Workmentioning

confidence: 99%

“…None of these previous works can handle the same amount of domain and mathematical dependencies supported by our FENCE framework. In Table 18 [2] Network Traic GAN/PSO OHE Linear Granados et al [28] Network Traic Iterative Range Stat optimization Sadeghzadeh et al [59] Packets UAP Range -Network Flows Network Bursts Han et al [31] Botnet GAN/PSO Range -Abusnaina et al [1] DDoS Detection Sample Range injection Ratio -Chen et al [13] Network Traic Iterative Range optimization -GAN Table 18. Comparison to existing work on evasion atacks in cybersecurity domains.…”

Section: Related Workmentioning

confidence: 99%

“…At any time during the iterative procedure, the input data point is modiied within the feasibility region, resulting in feasible adversarial examples. Existing evasion attacks in constrained environments, such as PDF malware detection [65,69], malware classiication [30,66], and network traic classiication [1,2,28,31,59] do not support the entire range of complex mathematical and domain-speciic dependencies as our FENCE framework. Moreover, some of these attacks result in worse performance [2] or operate only in a speciic domain [59] or feature space [2,28].…”

Section: Introductionmentioning

confidence: 99%

“…(1) We introduce a general evasion attack framework FENCE for constrained application domains that supports a range of mathematical dependencies in feature space and two optimization approaches. (2) We apply FENCE to two cyber security applications using diferent datasets and feature representations: a malicious network connection classiier, and a malicious domain detector, to generate feasible adversarial examples in these domains. (3) We extensively evaluate FENCE for these applications, compare our attacks with several baselines, and quantify the adversarial success at diferent perturbations.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

FENCE: Feasible Evasion Attacks on Neural Networks in Constrained Environments

Chernikova

Oprea

2022

ACM Trans. Priv. Secur.

View full text Add to dashboard Cite

As advances in Deep Neural Networks (DNNs) demonstrate unprecedented levels of performance in many critical applications, their vulnerability to attacks is still an open question. We consider evasion attacks at testing time against Deep Learning in constrained environments, in which dependencies between features need to be satisfied. These situations may arise naturally in tabular data or may be the result of feature engineering in specific application domains, such as threat detection in cyber security. We propose a general iterative gradient-based framework called FENCE for crafting evasion attacks that take into consideration the specifics of constrained domains and application requirements. We apply it against Feed-Forward Neural Networks trained for two cyber security applications: network traffic botnet classification and malicious domain classification, to generate feasible adversarial examples. We extensively evaluate the success rate and performance of our attacks, compare their improvement over several baselines, and analyze factors that impact the attack success rate, including the optimization objective and the data imbalance. We show that with minimal effort (e.g., generating 12 additional network connections), an attacker can change the model’s prediction from the Malicious class to Benign and evade the classifier. We show that models trained on datasets with higher imbalance are more vulnerable to our FENCE attacks. Finally, we demonstrate the potential of performing adversarial training in constrained domains to increase the model resilience against these evasion attacks.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

FENCE: Feasible Evasion Attacks on Neural Networks in Constrained Environments

Chernikova

Oprea

2022

ACM Trans. Priv. Secur.

View full text Add to dashboard Cite

show abstract

“…Alhajjar et al [29] explored utilizing particle swarm optimization (PSO), genetic algorithm (GA), and GANs to generate AEs for network traffic. The performance of these generation techniques was assessed over SVM, DT, NB, KNN, RF, MLP, Gradient Boosting (GB), LR, Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), and Bagging (BAG) using the NSL-KDD and UNSW-NB15 datasets.…”

Section: A Generation Of Aes To Attack Ml-based Nids Modelsmentioning

confidence: 99%

Adversarial Machine Learning In Network Intrusion Detection Domain: A Systematic Review

Alatwi¹,

Morisset²

2021

Preprint

View full text Add to dashboard Cite

show abstract

StinAttack: A Lightweight and Effective Adversarial Attack Simulation to Ensemble IDSs for Satellite- Terrestrial Integrated Network

Zhuang

Sun

Zhang

et al. 2022

2022 IEEE Symposium on Computers and Communications (ISCC)

View full text Add to dashboard Cite

Despite being widely used in network intrusion detection systems (NIDSs), machine learning (ML) has proven to be highly vulnerable to adversarial attacks. White-box and black-box adversarial attacks of NIDS have been explored in several studies. However, white-box attacks unrealistically assume that the attackers have full knowledge of the target NIDSs. Meanwhile, existing black-box attacks can not achieve high attack success rate due to the weak adversarial transferability between models (e.g., neural networks and tree models). Additionally, neither of them explains why adversarial examples exist and why they can transfer across models. To address these challenges, this paper introduces ETA, an Explainable Transfer-based Black-Box Adversarial Attack framework. ETA aims to achieve two primary objectives: 1) create transferable adversarial examples applicable to various ML models and 2) provide insights into the existence of adversarial examples and their transferability within NIDSs. Specifically, we first provide a general transfer-based adversarial attack method applicable across the entire ML space. Following that, we exploit a unique insight based on cooperative game theory and perturbation interpretations to explain adversarial examples and adversarial transferability. On this basis, we propose an Important-Sensitive Feature Selection (ISFS) method to guide the search for adversarial examples, achieving stronger transferability and ensuring traffic-space constraints. Finally, the experimental results on two NIDSs datasets show that our method performs significantly effectively against several classical and state-of-the-art ML classifiers, outperforming the latest baselines. We conduct three interpretation experiments and two cases to verify our interpretation method's correctness. Meanwhile, we uncover two major misconceptions about applying machine learning to NIDSs systems.

show abstract

Adversarial Machine Learning in Network Intrusion Detection Systems

Cited by 5 publications

References 0 publications

FENCE: Feasible Evasion Attacks on Neural Networks in Constrained Environments

FENCE: Feasible Evasion Attacks on Neural Networks in Constrained Environments

Adversarial Machine Learning In Network Intrusion Detection Domain: A Systematic Review

StinAttack: A Lightweight and Effective Adversarial Attack Simulation to Ensemble IDSs for Satellite- Terrestrial Integrated Network

Contact Info

Product

Resources

About