Toward developing a systematic approach to generate benchmark datasets for intrusion detection

By Ali Shiravi, Hadi Shiravi, Mahbod Tavallaee, Ali Akbar Ghorbani. Computers & security, 2012

1,339 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Information Systems

View Paper: https://www.semanticscholar.org/paper/846fcf30dc75f04886092891e754791e9704f69f

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

In Computer Networks and Communications

In Information Systems

Citations in the corpus

DeepDefense: Identifying DDoS Attack via Deep Learning (2017, methodology): “We train our deep learning models with a largescale dataset, UNB ISCX Intrusion Detection Evaluation 2012 DataSet (We use ISCX2012 for short in rest paper) [9] [10], to solve complicated recognition problems.”
A survey of network anomaly detection techniques (2016, neutral): “ISCX 2012 (Shiravi et al., 2012): It is developed by Information Security Centre of Excellence at University of New Brunswick.”
A survey of intrusion detection in Internet of Things (2017, background): “The most idealistic methodology for evaluating IDSs is running the system over real labeled network traces with an extensive set of intrusions (Shiravi et al., 2012).”
Deep Learning Approach for Intelligent Intrusion Detection System (2019, background): “In [56] generated a new dataset following two different proﬁle system in which one system was for generating attacks and other one was for normal activities.”
An empirical comparison of botnet detection methods (2014, methodology): “However, these datasets are difficult to create (Lu et al., 2009) and usually end up being suboptimal (Shiravi et al., 2012), i.e., they lack some important features, such as ground-truth labels, heterogeneity or real-world traffic.”
Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research (2022, background): “[106] UNB ISCX 2012 2012 1027 The Canadian Institute for Cybersecurity at the University of New Brunswick (UNB) established UNB ISCX 2012 in 2012.”
A Survey of Deep Learning Methods for Cyber Security (2019, methodology): “Using two datasets, CTU-UNB (CTU-13 59; UNB-ISCX 2012 [151]; Shiravi et al. [152]) and Contagio-CTU-UNB, Yu et al. [153] were able to achieve accuracies exceeding 98.5% on two-, six, and eight-class problems.”
Cybersecurity for industrial control systems: A survey (2020, methodology): “As a part of our future research, we aim to prepare hybrid datasets using multiple publicly available datasets such as UNSW (University of New South Wales) dataset [74], ISOT dataset [68], Lawrence Berkeley National Lab (LBNL) dataset [73], Information Security Center of Excellence (ISCX) [76], next”
Survey of intrusion detection systems: techniques, datasets and challenges (2019, methodology): “In this dataset, real network traffic traces were analyzed to identify normal behaviour for computers from real traffic of HTTP, SMTP, SSH, IMAP, POP3, and FTP protocols (Shiravi et al., 2012).”
A Detailed Investigation and Analysis of Using Machine Learning Techniques for Intrusion Detection (2019, methodology): “ISCX-IDS attack dataset [78] is not publicly available.”
InSDN: A Novel SDN Intrusion Dataset (2020, methodology): “• ISCX2012 [17]: The authors used two profiles to generate data traffic based on a simulated network environment.”