Detecting Aimbot Usage in Minecraft Using a Long Short-Term Memory Model
Bibliographic record
Abstract
The gaming industry has long been at the cutting edge of technology, sometimes at the cost of proper game security. This has lead to an industry of cheaters, in particular among online video games. The ability to catch cheaters is of interest to game server operators who want to maintain integrity and trust with their player-base. A form of cheating that is particularly problematic is the use of aiming robots (aimbots) that use client-side hacks to lock onto targets and perform maximum damage. Aimbots are common in first-person style player-vs-player type video games where they have the most potential to give the cheater a significant unfair advantage. Minecraft, for example, is a game that has a large online player base who enjoy player-vs-player combat mini-games. Hacked clients are readily available to the average player and thus there is a strong need to be able to detect this cheating behaviour on the server side. Significant consideration toward fairness must be given to any solution that attempts to detect behaviour that would result in disciplinary action. Thus, it is important to maintain very high levels of accuracy as to avoid the false flagging of players who did not cheat. Further, any system that does not detect true aimbotters with very high accuracy would undermine player trust in the system. Therefore, we propose in this paper, a neural network approach to aimbot detection using Long Short-Term Memory to classify cheaters based on their movements over time. Our network achieves very high accuracy at high confidence levels, providing a notable improvement over a Gated Recurrent Network on the same data. We believe the network at these accuracy levels could have significant practical use in real-world servers.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".