Study Proposes Novel System to Detect Illegal Mobile Gambling Sites
The gambling market as a whole is among the world’s most regulated industries. It has been for centuries. In such a munificent trade, the potential for corruption is astronomical. But it seems every time authorities get a handle on regulatory compliance, something comes along to wrest it away. In this day and age, it’s the slippery slope of mobile technology that’s making it so difficult to detect and eliminate illegal gambling operations.
It’s a problem that poses a multitude of threats, far beyond that of ‘unauthorized access’, and one that a group of researchers are determined to solve. With funding from the Agency for Defense Development, Moohong Min (University College, Sungkyunkwan University, Seoul), Jemin J. Lee (Center for Information Security Technology, Korea University, Seoul) and Kyungho Lee (Department of Information Security, Korea University, Seoul) have come up with a novel system, described in their collaborative study:
Illegal Gambling Sites are More Dangerous Than You May Think
If you’ve been following the industry as long as I have (mid-2000s), you may have a skewed perception of the true threat illegal online gambling poses to soceity.
In the early days of the internet, major countries like France, Spain, the United States, and others threw a blanket-ban over online gambling. They deemed it 100% illegal, despite having little resources to enforce such prohibition.
Many iGaming operators chose to access these jurisdictions anyway. Some of them were perfectly reputable companies, utilizing loopholes to circumvent the law. Players saw these websites as saviors for providing them with a service they believed they deserved access to, but were ultimately denied by government oppression. These illegal gambling operations are hardly the threats we’re talking about today.
The real threat comes from corrupt operators with rogue intentions; gambling sites that look to victimize their players by any means possible. These are the most harmful type. They might sell a user’s personal and financial information to the highest bidder. They could adjust the odds of their gaming software to ensure greater losses for their players. Or, they could simply refuse to pay out winnings, disappearing into the night with your bankroll in tow. They don’t care about underage gambling, addictive behavior, or the psychological harm it causes, imposing no preventative restrictions. They are the underbelly of industry, and the reason I’m highlighting this study today.
Systematic Detection of Illegal Mobile Gambling Sites
The idea behind the system is to identify the URLs of illegal gambling sites by algorithmic data mining of targeted SMS text messages. That’s a lot of big words, I know – bear with me and I’ll explain as briefly as possible.
Illegal online gambling (IOG) sites cannot advertise in any public forum. Traditionally, they would rely on word of mouth (i.e. existing members referring their friends). It’s effective, but only to a small degree. What’s proven much more effective is spam advertising through short message service (SMS); text messaging, as most of us know it.
Many authorities have set up reporting mechanisms that give mobile users the ability to instantly report spam messages. When a user taps the ‘report message’ button on their device, it sends a copy of that text to a government agency for investigation. But what these researchers are proposing is an AI system that could detect illegal gambling links much sooner.
“This study proposes a system based on artificial intelligence to sort illegal gambling messages from reported suspicious messages with a detection accuracy rate of 97%. Moreover, this study finds that illegal messages exhibit several patterns, including features that revise URLs to stop them from being filtered automatically. By reversing such patterns, the URL information can be reconstructed, and it will be easier for IOG websites to be automatically reported and taken down.”
Means of Blocking Illegal Online Gambling URLs
Detection is only the beginning. As the technology systematically identifies and reports IOGs to the proper authorities, several more steps must take place to eliminate the website as a public threat. It starts with proving that the URL truly belongs to an illegal gambling operation. That means screening the website for illegal activity and providing screenshots. Once enough evidence is collected, authorities can take action to block the website.
It’s a 6-step process, start to finish:
Crawling URLs associated with illegal online gambling;
Collecting suspicious URLs and any supporting evidence;
Submitting URLs and evidence to the proper authorities;
Authoritative review to verify designation;
URLs verified to be illegal are forwarded to the internet service provider (ISP)
ISP initiates block against URLs
Is The World Ready for AI Detection via SPAM SMS?
The easy answer to this question is, “No”. The study comes out of Korea, where laws surrounding the internet and mobile technology are much more strict than most regions of the world. For example, the researchers point out that, “Spam messages containing the term “gamble” are illegal in South Korea”. This makes it easy for AI technology to parse SMS for illegal activity.
That’s not to say every government should hold its thumb so tightly over its mobile-using populace. It’s simply a presiding factor in the potential success of the system in Korea and similar nations. Such laws would hardly fly in places like North America, where freedom of speech reigns supreme.
The same type of detection system could still be effective worldwide. The difference would be in the degree of challenge for the personnel in charge of weeding through a larger batch of messages for those with illegal online gambling URLs. Still, it provides a technological “cornerstone”, as noted in the researchers’ conclusion.
“This work provides a cornerstone for future researchers interested in detecting illegal gambling and other problematic content that employs spam mass marketing. In the future, we plan to identify optimal parameters (such as the number of hidden layers) centered on DNN and continue research on methods to improve performance. The results of these experiments are limited to text-based data, so further investigation is needed for image-based spam messages.”
Do you have an interest in reviewing the process for which their AI system algorithmically detects illegal mobile gambling URLs via spam SMS? If you’ve got the programming knowledge to make sense of it, be my guest. You’ll find it all right here.
#1 Canadian-Friendly Casino
Jackpotcity.com is our editorial pick for your gaming needs. Currently offering an entire suite of casino games, as well as a wide range of Canadian deposit options, JackPotCity truly offers world-class gaming.
Adalene Lucas: is our jack of all trades here at DBC. She is a skilled coder, gambler, writer and webmaster. She lives in Manitoba where she enjoys the lush landscapes and camping near Tulabi Falls. Nature gives her inspiration to write. When she's not immersed in nature, her favorite words are "game theory". She lives with her husband and their two Labradors, Kophy and Whisper.