Datasets

API Call Logs

The complete API Call Logs can be downloaded from here. Kindly contact zubair [dot] shafiq [at] nexginrc [dot] org for any queries.

API Call "Sequence-only" Dataset

The API Call (Sequence only) dataset can be downloaded from here. Kindly contact zubair [dot] shafiq [at] nexginrc [dot] org for any queries.

Embedded Malware Dataset

Embedded Malware Dataset was created using the tool called ‘NERGAL’. This extensive dataset is built on the top of VX Heavens Virus Dataset.

Due to privacy and misuse concerns, we are not publicly providing `NERGAL' and the embedded malware dataset. To gain access, kindly email at zubair [dot] shafiq [at] nexginrc [dot] org from your institutional email address explaining the intended use.

Endpoint Worm Scan Dataset

Worm Scan Dataset was originally collected at Michigan State University (MSU), USA. It consists of two parts, (1) Worm traces and, (2) Benign traces. Worm traffic traces consist of traffic logs of various real and simulated worms. They include Blaster, Dloader-NY, Forbot-FU, MyDoom-A, RBOT.CCC, Rbot-AQJ, Sdbot-AFR, SoBig.E, Zotob.G, Witty, CodeRed II and Sim Src Port. Benign traffic traces consist of 12 months traffic logs of 13 different endpoints which include office, home and university desktops and laptops.

Each entry in the log file has the following 6 fields:

< session id, direction, src port, dst port, protocol, timestamp > . More details can be found in our publications section.