Shoot the Honey, Cloak the Player: Towards Zero-Runtime-Overhead Proactive Defense and Detection for Visual Game Cheating

arXiv:2606.25734 · cs.CR · Submitted 2026-06-24 · Read on arXiv

cs.CR

Submitted: 2026-06-24

Updated: 2026-09-08

Comments: This work was accepted at ACM CCS 2026

Code: https://github.com/ai-aimbot/AIMr

License: http://creativecommons.org/licenses/by-nc-nd/4.0/

The gist: Visual aimbots have emerged as a serious cheating threat in first-person shooter (FPS) games, as they evade existing anti-cheat defenses by operating only on rendered frames rather than game memory.

Terminology

Abstract

Visual aimbots have emerged as a serious cheating threat in first-person shooter (FPS) games, as they evade existing anti-cheat defenses by operating only on rendered frames rather than game memory. However, existing defenses fail to provide an end-to-end solution: post-hoc behavior detectors cannot protect match integrity in real time and are increasingly fragile against human-mimicking aimbots, while proactive runtime defenses often lack accountability, incur substantial overhead, or require intrusive system integration. We present AimTrap, the first end-to-end visual-aimbot defense that combines runtime protection with post-game detection through two adversarial texture mechanisms. Adversarial Camouflage Textures (ACT) hide real players from aimbots, while Adversarial Honeypot Textures (AHT) lure aimbots into locking onto fake targets, yielding strong evidence of cheating. AimTrap integrates differentiable rendering with Expectation over Renderings for robust 3D texture synthesis and analyzes honeypot-interaction trajectory to facilitate cheating attribution. In real-game evaluation against a visual aimbot, ACT achieves 85.1% defense success, AHT achieves 96.9%. Compared with prior baselines, AimTrap also achieves extremely low false-positive rates with negligible runtime overhead, demonstrating a practical end-to-end defense.

Sources

Related papers