Adversarial Deep Learning approach detection and defense against DDoS attacks in SDN environments

Novaes, Matheus P.; Carvalho, Luiz F.; Lloret, Jaime; Proença, Mário Lemes

doi:10.1016/j.future.2021.06.047

Cited by 94 publications

(53 citation statements)

References 58 publications

(58 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As can be observed from Table 5, the classifier trained only using the dataset can correctly classify the generated benign and DDoS instances when they look like benign and DDoS instances from the dataset. Therefore, this classifier, which is trained only using the dataset, will be able to classify both generated adversarial attack instances and benign instances correctly, similar to the discriminator model trained by [38] as long as there are no manual changes made in the input features of the generated instances. But from Table 6, it is concluded that such a classifier will not be able to predict the attack if the values of DDoS-specific attack features are changed in benign instances to make them malicious.…”

Section: Resultsmentioning

confidence: 99%

“…For this purpose, the GAN framework can generate new DDoS instances and check if the classifier is robust enough to detect such generated synthetic instances. [38] have implemented a GAN-based framework wherein they have used the discriminator model to detect DDoS attacks. Although the discriminator model in GANs can help make the system less sensitive to adversarial attacks, traditional GANs are known to suffer from problems like vanishing gradients and mode collapse.…”

Section: Detecting Ddos Attacks Using Adversarial Machinementioning

confidence: 99%

See 1 more Smart Citation

Enhanced Security Against Volumetric DDoS Attacks Using Adversarial Machine Learning

Shroff

Walambe

Singh³

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

With the increasing number of Internet users, cybersecurity is becoming more and more critical. Denial of service (DoS) and distributed denial of service (DDoS) attacks are two of the most common types of attacks that can severely affect a website or a server and make them unavailable to other users. The number of DDoS attacks increased by 55% between the period January 2020 and March 2021. Some approaches for detecting the DoS and DDoS attacks employing different machine learning and deep learning techniques are reported in the literature. Recently, it is also observed that the attackers have started leveraging state-of-the-art AI tools such as generative models for generating synthetic attacks which fool the standard detectors. No concrete approach is reported for developing and training the models which are not only robust in the detection of standard DDoS attacks but which can also detect adversarial attacks which are created synthetically by the attackers with harmful intentions. To that end, in this work, we employ a generative adversarial network (GAN) to develop such a robust detector. The proposed framework can generate and classify the synthetic benign (normal) and malignant (DDoS) instances which are very similar to the corresponding real instances as evaluated by similarity scores. The GAN-based model also demonstrates how effectively the malicious actors can generate adversarial DDoS network traffic instances which look like normal instances using feature modification which are very difficult for the classifier to detect. An approach on how to make the classifiers robust enough to detect such kinds of deliberate adversarial attacks via modifying some specific attack features manually is also proposed. This work provides the first step towards developing a generic and robust detector for DDoS attacks originating from various sources.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Detecting Ddos Attacks Using Adversarial Machinementioning

confidence: 99%

Enhanced Security Against Volumetric DDoS Attacks Using Adversarial Machine Learning

Shroff

Walambe

Singh³

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Novaes et al [49] used Generative Adversarial Network (GAN) framework to alleviate the impact of DDoS attacks in SDNs. The emulated and the public dataset i.e.…”

Section: Deep Learning Based Solutionsmentioning

confidence: 99%

“…Scapy or Hping3, and targeted only the network layer of the OSI model, without including the attacks against the application layer. Novaes et al [49] GAN framework to alleviate the impact of DDoS attacks in SDNs.…”

Section: Kalkan Et Al [32]mentioning

confidence: 99%

A Flow-Based Anomaly Detection Approach With Feature Selection Method Against DDoS Attacks in SDNs

Elsayed

Le-Khac

Azer

et al. 2022

IEEE Trans. Cogn. Commun. Netw.

View full text Add to dashboard Cite

“…Fase ini untuk memonitor secara real-time untuk mendeteksi serangan DDoS. Ini bisa menjadi sulit jika penyerang memanfaatkan botnet yang terletak di beberapa lokasi di seluruh dunia (Novaes et al, 2021) (Marta et al, 2020). Sistem Deteksi instruksi adalah solusi yang umum digunakan untuk menganalisis dan mendeteksi serangan DDoS.…”

Section: Pemantauanunclassified

Impact of Feature Selection Methods on Machine Learning-based for Detecting DDoS Attacks : Literature Review

Faiz¹,

Somantri²,

Supriyono³

et al. 2022

JITE

View full text Add to dashboard Cite

Cybersecurity attacks are becoming increasingly sophisticated and increasing with the development of technology so that they present threats to both the private and public sectors, especially Denial of Service (DoS) attacks and their variants which are often known as Distributed Denial of Service (DDoS). One way to minimize this attack is by using traditional mitigation solutions such as human-assisted network traffic analysis techniques but experiencing some limitations and performance problems. To overcome these limitations, Machine Learning (ML) has become one of the main techniques to enrich, complement and enhance the traditional security experience. The way ML works are based on the process of data collection, training and output. ML is influenced by several factors, one of which is feature engineering. In this study, we focus on the literature review of several recent studies which show that the feature selection process greatly impacts the level of accuracy of this ML. Datasets such as KDD, UNSW-NB15 and others also affect the level of accuracy of ML. Based on this literature review, this study can observe several feature engineering strategies with relevant impacts that can be chosen to improve ML solutions on DDoS attacks.

show abstract

Adversarial Deep Learning approach detection and defense against DDoS attacks in SDN environments

Cited by 94 publications

References 58 publications

Enhanced Security Against Volumetric DDoS Attacks Using Adversarial Machine Learning

Enhanced Security Against Volumetric DDoS Attacks Using Adversarial Machine Learning

A Flow-Based Anomaly Detection Approach With Feature Selection Method Against DDoS Attacks in SDNs

Impact of Feature Selection Methods on Machine Learning-based for Detecting DDoS Attacks : Literature Review

Contact Info

Product

Resources

About