This dataset contains network traffic sampled during a browsing session. It contains normal as well as streaming traffic, to be used in order to evaluate the models trained for network streaming traffic prediction.

Access: Only researchers and LEAs upon request

Link: TUB

This dataset contains the memory accesses induced by the execution of a protected virtual machine.

Access: Only researchers and LEAs upon request

Link: TUB

A dataset for the research of domain generation algorithms (DGAs) and machine learning. The dataset contains more than 90m domains and more than 100 families.

Access: Public

Link: Zenodo

A dataset with benign and malicious MS Office documents and the extracted features from static analysis.

Access: Public

Link: Zenodo

We provide a large-scale dataset of the messages exchanged publicly by the streamers and viewers during the live broadcasts of users identified as adult content producers from the LiveMe platform, a major Social Live Streaming Service (SLSS). The dataset comprises 39,382,838 chat messages exchanged by 1,428,284 users, in the context of 293,271 live broadcasts during a period of approximately two years, from July 2016 to June 2018. The analysis of this dataset can be found in our paper "Large-scale analysis of grooming in modern social networks" (arXiv:2004.08205 [cs.SI]).

Access: Only researchers and LEAs upon request

Link: Zenodo

This repository contains a dataset for the research of domain generation algorithms (DGAs) and machine learning. More precisely, it targets dictionary-based DGAs. The analysis of this dataset can be found in our paper "Exploiting Statistical and Structural Features for the Detection of Domain Generation Algorithms".

Access: Public

Link: Zenodo