Generation of a new IDS test dataset: Time to retire the KDD collection

By Gideon Creech, Jiankun Hu. IEEE Wireless Communications and Networking Conference, 2013

321 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Signal Processing

View Paper: https://www.semanticscholar.org/paper/1a3f697d2951d65708558583c35a0bbd6b2de175

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Arash Habibi Lashkari
2. Mohamed Amine Ferrag
3. Leandros A. Maglaras
4. Helge Janicke
5. Sotiris K. Moschoyiannis
6. Ali Akbar Ghorbani
7. Iman Sharafaldin
8. Nhien-An Le-Khac

In Computer Networks and Communications

1. Mohamed Amine Ferrag
2. Leandros A. Maglaras
3. Nhien-An Le-Khac
4. Mahmoud Said Elsayed
5. Anca Delia Jurcut
6. Arash Habibi Lashkari
7. Helge Janicke
8. Sotiris K. Moschoyiannis

In Signal Processing

1. Abdun Naser Mahmood
2. Arash Habibi Lashkari
3. Iman Sharafaldin
4. Ali Akbar Ghorbani
5. Mohiuddin Ahmed
6. Ernesto Damiani
7. Zhibo Zhang
8. Fatma Taher

Citations in the corpus

• UNICORN: Runtime Provenance-Based Detector for Advanced Persistent Threats (2020, background): “…for several reasons: A) many IDS are not open-source; B) existing public IDS datasets are either outdated [4], [85] or require a translation [28], [50], [51] from, e.g., syscall traces to data provenance, which is challenging and sometimes impossible (due to lack of information); C) systems…”
• Malware traffic classification using convolutional neural network for representation learning (2017, background): “…learning approaches focus on feature selection techniques, many current public traffic datasets are flow features datasets other than raw traffic datasets, e.g. famous KDD CUP1999 and NSL-KDD provide pre-defined 41 features in their dataset [11], and there are many similar datasets, such as [14].”
• Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research (2022, background): “[112] ADFA-LD 2013 281 The ADFA-LD12 represents a worthy successor to the KDD collection.”
• A survey of network anomaly detection techniques (2016, methodology): “Creech and Hu (2013) introduced a publicly available dataset ADFA-LD12, which is a representative of the modern attack structure and methodology.”
• InSDN: A Novel SDN Intrusion Dataset (2020, result): “In addition, we have also studied the previous work in [17], [18], [46]–[48] to generate a comprehensive dataset and to take into consideration the setting up of the new”
• Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study (2020, methodology): “14) ADFA2013 dataset: [100] This dataset is proposed by Creech and Hu [101], [133] which uses payloads and vectors to attack the Ubuntu OS.”
• Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization (2018, methodology): “ADFA (University of New South Wales 2013): This dataset includes normal training and validating data and 10 attacks per vector (Creech and Hu, 2013).”
• A Survey of Network-based Intrusion Detection Data Sets (2019, background): “intrusion detection data sets like ADFA [26] are not considered”
• Survey on SDN based network intrusion detection system using machine learning approaches (2018, methodology): “The ADFA-LD12 dataset is a worthy successor for the KDD dataset [56], and the UNSW-NB15 dataset [57] was also used for academic research purpose.”