Raiders,
Anti-cheat at Embark is a studio-wide effort that protects every player across our games. With ARC Raiders Riven Tides now live, we wanted to share where things stand, what we're building, and how we think about and solve the harder problems when it comes to fair play in ARC Raiders.
How We Protect Fair Play
Our anti-cheat stack combines kernel-level protection from Easy Anti-Cheat with detection capabilities powered by machine-learning (ML) models, trained on a constant flow of player telemetry. Several additional layers sit behind these, which we don't disclose for operational security.
Kernel-level detection is a necessity because most commercial cheats operate within that space. Without it, we'd have little to no visibility into the tools doing the most damage. We're currently testing a new kernel-level solution that we expect will sharpen both detection and precision throughout Speranza and the Rust Belt.
On the ML side, input telemetry analysis has become one of our most effective tools. We've trained and deployed a set of models dedicated to this, and we've been working with Anybrain on this research since the start.
Accessibility and Intent
Managing accessibility devices is one of the harder problems in anti-cheat. Players who rely on this equipment need to be able to play, and because official solutions are expensive, players often use lesser-known devices to achieve the same goal. Of course, in the wrong hands, these tools can also be used to cheat.
The signal we care about is intent. Our systems analyze telemetry and communication patterns to distinguish legitimate accessibility use from abuse, so players who depend on these devices to play can keep playing. This is a process that continues to be refined, but we’re dedicated to the work and the results we’ve seen thus far.
Official devices from major platforms are well known and common, so we’re able to detect them with accuracy and understand the intent behind their use. Our partners at Anybrain are constantly expanding on their knowledge of various accessibility hardware, helping us detect more and refine the use cases, making our ML detection smarter, more reliable, and more accessible with time.
How Ban Appeals Work
Every ban appeal is reviewed by a person on our team. The process isn't automated, and we keep refining it as we learn more about the cases that come through. A fair and accurate appeals process matters to us across every game we make, and we treat it as a permanent area of investment rather than a finished system.
While it may be frustrating to wait for an answer and to get the pre-written responses that our agents need to use in order to maintain consistency, we look into each case to ensure fair gameplay and to test and refine the systems and models that have been put in place to keep the game fair and fun.
Stay tuned for more updates from us in the near future!
Until then, we’ll see you Topside!
(We’ve got eyes everywhere)
The Anti-cheat Team