GDC is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

View, browse and sort the ever-growing list of sessions by day, pass type, topic, and format. With this Session Viewer, you can view GDC 2023 session details and speakers, and share your favorites via social media. You will be able to build your schedule and access it during the show via export or Mobile App, once live. Sessions do fill up and seating is first come, first serve, so arrive early to sessions that you would like to attend.

Online Game Technology Summit: Hallucinations: Baiting Cheaters Into Self-Identifying by Reversing Detection

David Durst  (PhD Candidate, Stanford University)

Carly Taylor  (Senior Manager, Security Strategy, Activision Publishing, Inc.)

Location: Room 3005, West Hall

Date: Monday, March 20

Time: 4:40 pm - 5:10 pm

Pass Type: All Access Pass, Summits Pass

Topic: Programming

Format: Lecture

Vault Recording: Video

Audience Level: All

Anti-cheat and cheat developers are locked in a cat and mouse cycle of detection and circumvention. Anti-cheat developers struggle to find new behavioral patterns that reliably identify cheating players imitating legitimate players, and cheat developers easily change the patterns.

This talk will discuss a complementary anti-cheat technique, hallucinations, that baits cheating players into identifying themselves.

Hallucinations are fake enemies imitating humans that legitimate players can't observe—but cheating players can, because their cheating programs treat the apparitions as real players. Reconfigurable hallucinations are particularly interesting because they may flip the cycle so anti-cheat developers solve an easier problem, reconfiguring hallucination imitation behavior, and cheat developers solve a harder problem, detecting hallucination behavior patterns.

The talk will provide an economic argument for why reconfigurable bait techniques may be a long-term strategy, a description of a hallucination implementation, and evidence that popular cheat programs treat one hallucination implementation as a real player.


Attendees will learn how a hallucination implementation injects fake players into the snapshot, how that implementation can be reconfigured with different policies for imitating real player behavior, and how the implementation approach may allow hallucinations to evolve with cheat programs.

Intended Audience

This is for developers and data scientists interested in anti-cheat techniques. Familiarity with multiplayer client-server architectures and FPS visibility computation techniques may be helpful but is not required.