network security

This dataset presents real-world IoT device traffic captured under a scenario termed "Active," reflecting typical usage patterns encountered by everyday users. Our methodology emphasizes the collection of authentic data, employing rigorous testing and system evaluations to ensure fidelity to real-world conditions while minimizing noise and irrelevant capture.

This dataset consists of “.csv” files of 4 different routing attacks (Blackhole Attack, Flooding Attack, DODAG Version Number Attack, and Decreased Rank Attack) targeting the RPL protocol, and these files are taken from Cooja (Contiki network simulator). It allows researchers to develop IDS for RPL-based IoT networks using Artificial Intelligence and Machine Learning methods without simulating attacks. Simulating these attacks by mimicking real-world attack scenarios is essential to developing and testing protection mechanisms against such attacks.

The dataset has been developed in Smart Connected Vehicles Innovation Centre (SCVIC) of the University of Ottawa in Kanata North Technology Park.

In order to define a benchmark for Machine Learning (ML)-based Advanced Persistent Threat (APT) detection in the network traffic, we create a dataset named SCVIC-APT-2021, that can realistically represent the contemporary network architecture and APT characteristics.  Please cite the following original article where this work was initially presented:

As an alternative to classical cryptography, Physical Layer Security (PhySec) provides primitives to achieve fundamental security goals like confidentiality, authentication or key derivation. Through its origins in the field of information theory, these primitives are rigorously analysed and their information theoretic security is proven. Nevertheless, the practical realizations of the different approaches do take certain assumptions about the physical world as granted.