Aim bots are nothing new in the world of competitive online gaming. But the possible existence of a virtually undetectable new machine learning-powered cheat for consoles has the gaming community in a bit of a fervor as of late.

Up front: We can’t confirm its existence, but the Anti-Cheat Police Department Twitter account posted footage of what it says is a legitimate AI-powered cheating software.

What makes this interesting is that it’s alleged to work on consoles. While consoles are typically more difficult to cheat on than PCs, due to the nature of their respective operating systems, it’s certainly not rare to come across people using aim assistance software (aim bots) or modified controllers.

However, it’s typically relatively easy to detect them. Whether you can see the modified interface in game replays from the cheater’s perspective (a feature common to FPS games) or the developers bake in methods for detecting non-human inputs and performances, there’s usually a way to squash cheats when they start propagating.

The big deal: In the above video, what we’re allegedly seeing is a player using a PC with a capture card to send real-time gaming data (ie: whatever’s on the TV screen) from their gaming console to a cheat program running on the PC.

The cheat program then uses what appears to be a fairly basic computer vision system to identify targets. It then sends spoofed commands to the player’s controller so that the console itself is fooled into thinking the player is controlling everything.

In game, the player just has to control their on-screen avatar’s movement and aim in the general direction of enemies. The software locks on to targets and automatically fires.

Quick take: This is an interesting modern twist on a classic gaming cheat. The existence of aim bots is, unfortunately, a common evil – even on consoles. But it’s typically more of a nuisance at the public lobbies level than it is on competitive circuits.

Fortunately, there’s almost nothing noteworthy about the machine learning used in a system like this. The only interesting thing here is that the PC program spoofs commands to the controller. This makes it virtually undetectable. At least by humans working alone.

Microsoft and Sony both have outstanding AI departments and they’re both heavily-invested in fighting cheating in video games – the esports market alone is expected to surpass $1 billion this year.

Microsoft’s developing AI systems to track and detect player skill evolution. This will allow them to determine with incredible accuracy when a player employs performance-enhancing software or devices. And Sony regularly patents new anti-cheat technology .

At the end of the day, this is just another round in the cat and mouse game between cheaters and developers.

H/t: Eurogamer

Trump accuses Twitter of promoting negative stories about him

President Trump’s love-hate relationship with Twitter hit another rocky patch today, when Agent Orange accused the platform of manipulating its trending topics to achieve the otherwise impossible feat of making him look bad.

Trump made the allegation on, what else, but Twitter. But defenders of truth and justice can rest assured: the matter is under investigation.

New algorithm scans through escort ads to find victims of trafficking

Scientists have developed an algorithm that scans online ads for escorts to identify human traffickers and their victims.

The algorithm, called InfoShield, searches for escort ads with strong similarities, which can be a sign of trafficking.

Per the study paper :

Law enforcement agencies typically look for HT cases manually. InfoShield is designed to speed up the search by detecting mini-clusters of ads, grouping them together, and summarizing the common parts.

“Our algorithm can put the millions of advertisements together and highlight the common parts,” said study co-author Christos Faloutsos in a statement . “If they have a lot of things in common, it’s not guaranteed, but it’s highly likely that it is something suspicious.”

Researchers at Carnegie Mellon University and McGill University adapted InfoShield from an algorithm used to spot anomalies in data, such as typos in hospital patient information.

In tests on escort listings that had already been identified as advertising victims of trafficking, InfoShield correctly flagged the ads with 84% precision. In addition, it didn’t incorrectly identify any of the listings as trafficking ads.

However, the team had to keep their findings private to protect the victims. To prove their algorithm worked, they applied it to tweets created by bots, which also typically tweet the same information in similar ways.

They found that InfoShield was also highly accurate at detecting the bots:

The team now hopes to see their research help victims of trafficking, and ultimately reduce human suffering.

You can read the study paper here .

Greetings Humanoids! Did you know we have a newsletter all about AI? You can subscribe to it right here .