Game Bot Detection

1. Description

This dataset was used at the 'Game bot detection track' of 'Information Security R&D Data Challenge 2019'.
It consists of user activity logs of AION*. Different, but consecutive, periods of logs were used for the preliminary and final rounds.

* An MMORPG serviced by NCSOFT since November 2008.

2. Challenge Summary and Data Conversion

 Round Log Period
 Preliminary 2010-04-16 ~ 2010-04-30 (15 days)
 Final 2010-05-01 ~ 2019-05-07 (7 days)

A total of 22 days of user activity logs were provided. (2010-04-16 ~ 2019-05-07)
Sensitive information, such as character name which may contain personally identifiable information, is deleted from the original log.
IP address, character identifier, account identifier are converted to other random values to avoid exposure of the real user.
* IP addresses and identifiers are converted by combining preliminary and final round dataset. Hence, a character who is active both preliminary and final log period will have same character identifier, unlike the dataset provided during the challenge.

List of labeled accounts

A list of valid accounts labeled whether the account is a game bot or not will be provided with the dataset. (0: normal, 1: game bot)
Only accounts that have one or more characters that are active for more than 3 hours during the log period were included in the list.
The banned list was provided by the game company to serve as the ground truth, and each banned user has been vetted and verified by human labor and active monitoring.

Field notes

  • actor, target: character identifier or NPC (Non-Player Character) identifier is recorded on these fields.
  • actor_account, target_account: account identifier or NPC (Non-Player Character) identifier is recorded on these fields.

3. Dataset Download

Please send a mail to Huy Kang Kim (cenda@korea.ac.kr) describing your identity and purpose of use.
(Total size: 184GB)

4. Related Publication

  • Kang, A. R., Jeong, S. H., Mohaisen, A., & Kim, H. K. (2016). Multimodal game bot detection using user behavioral characteristics. SpringerPlus, 5(1), 1-19.
  • Kwon, H., Mohaisen, A., Woo, J., Kim, Y., Lee, E., & Kim, H. K. (2016). Crime scene reconstruction: Online gold farming network analysis. IEEE Transactions on Information Forensics and Security, 12(3), 544-556.
  • Lee, E., Woo, J., Kim, H., Mohaisen, A., & Kim, H. K. (2016). You are a Game Bot!: Uncovering Game Bots in MMORPGs via Self-similarity in the Wild. Network and Distributed System Security Symposium (NDSS).

5. See Also




Comments