Mastercard has introduced Decision Intelligence, a comprehensive decision and fraud detection service which uses AI to help financial institutions increase the accuracy of real-time approvals of genuine transactions and reduce false declines.
This is the first use of AI being implemented on a global scale directly on the Mastercard network.
Current decision-scoring products are focused primarily on risk assessment, working within predefined rules. Decision Intelligence is a radical new approach that goes much further. It takes a broader view in assessing, scoring and learning from each transaction. That score then enables the card issuer to apply the intelligence to the next transaction.
“We are solving a major consumer pain point of being falsely declined when trying to make a purchase,” said Ajay Bhalla, president of enterprise risk and security, Mastercard. “By using AI technology on our global network, we’re helping financial institutions and merchants improve approval rates – and the consumer experience.”
How It Works
Building on other proprietary services, Decision Intelligence is a new way of solving an old problem using sophisticated algorithms to provide a predictive score to the issuer, based on intelligent analysis. They then incorporate that information into their existing fraud mitigation efforts. Alternatively, issuers can activate the holistic Mastercard tool, which makes data-driven, real-time decisions tailored to the account, including defined alert and decline thresholds.
The smart technology behind Decision Intelligence examines how a specific account is used over time to detect normal and abnormal shopping spending behaviours. In doing so, it leverages account information like customer value segmentation, risk profiling, location, merchant, device data, time of day, and type of purchase made.
Delivering Value in Every Tap, Dip or Swipe
Over the last few years, the industry has been increasingly focused on protecting payments and combating fraud, which is why striking the right balance in approving transactions and managing fraud is important.
“We estimate that in the U.S. alone, the value of false declines is more than 13 times the total amount lost to actual card fraud,” said Al Pascual, senior vice president, research director and head of fraud and security at Javelin Strategy & Research. “Applying machine learning to decision-scoring is a new way of creating a positive consumer experience, while also minimizing fraud.”
The addition of AI as a core component of the Mastercard network will deliver an enhanced fraud score for every transaction. This new functionality can help improve the accuracy of real-time approvals of genuine transactions and reduce false declines. In specific verticals, like fuel or ATM, the information could be used in real-time to react to potential concerns much quicker, reducing operational expenses like chargebacks.
This technology is a core feature on the enhanced World Elite platform and it also supports all Mastercard brands and products across all markets.
Cons exploit Telegram ICO
Kaspersky Lab researchers have uncovered dozens of highly convincing fake websites claiming to be investment sites for an initial coin offering (ICO) by the Telegram messaging service. Many of these websites appear to belong to the same group. In one case alone, tens of thousands of US dollars’ worth of cryptocurrency were stolen from victims believing they were investing in ‘Grams’, Telegram’s rumoured new currency. Telegram has not officially confirmed an ICO and has warned people about fraudulent investor sites.
In late 2017, stories started to circulate that the Telegram messaging service was launching an initial coin offering (ICO) to finance a blockchain platform based on its TON (Telegram Open Network) technology. Unverified technical documentation was posted online, but there appears to have been no confirmation from Telegram itself. The resulting confusion seems to have allowed fraudsters to capitalise on investor interest by creating fake sites and stealing vast sums of money.
Kaspersky Lab researchers have discovered dozens of such sites, possibly belonging to the same group, claiming to sell tokens for ‘Grams’ and inviting investors to pay with cryptocurrencies including Bitcoin, Ethereum, lice litecoin, dash and Bitcoin dash. A record of transactions on one site revealed that the scammers were able to steal at least $35,000 US dollars’ worth of Ethereum from investors.
The researchers found that some of the websites were so convincing that even after Telegram and others began to issue warnings, they were still able to recruit potential investors. Most use a secure connection, require registration and generate a unique online wallet for each new victim, making it harder to track the money.
Judging by the content of the fake websites, it appears they may have common ownership. For example, several have the exactly the same ‘Our Team’ section.
“ICOs are a fairly risky investment and many people don’t yet fully understand how they work, so it is not surprising that high quality fake websites, with seemingly reassuring features such as a secure connection and registration are successful at luring people in. People wishing to invest in an ICO would do well to check with the company behind it and make sure they know exactly who they are giving their money to, or they may never see it again,” said Nadezhda Demidova, Lead Web-Content Analyst, Kaspersky Lab.
Kaspersky Lab offers the following advice for users considering investing in an ICO:
- Check for warning signs: for example, some of the fake Telegram ICO websites had the same wrong image next to the name of Telegram’s Chief Product Officer.
- Do your homework: always check with the brand’s official site to verify the legitimacy of the investment site and, if necessary contact the company’s ICO teams before investing any money or currency.
- Use reliable security solutions such as Kaspersky Internet Security and Kaspersky Internet Security for Android, which will warn you if you try to visit fake internet pages.
Crouching Yeti strikes
Kaspersky Lab has uncovered infrastructure used by the Russian-speaking APT group Crouching Yeti, also known as Energetic Bear, which includes compromised servers across the world.
According to the research, numerous servers in different countries were hit since 2016, sometimes in order to gain access to other resources. Others, including those hosting Russian websites, were used as watering holes.
Crouching Yeti is a Russian-speaking advanced persistent threat (APT) group that Kaspersky Lab has been tracking since 2010. It is best known for targeting industrial sectors around the world, with a primary focus on energy facilities, for the main purpose of stealing valuable data from victim systems. One of the techniques the group has been widely using is through watering hole attacks: the attackers injected websites with a link redirecting visitors to a malicious server.
Recently Kaspersky Lab has discovered a number of servers, compromised by the group, belonging to different organisations based in Russia, the U.S., Turkey and European countries, and not limited to industrial companies. According to researchers, they were hit in 2016 and 2017 with different purposes. Thus, besides watering hole, in some cases they were used as intermediaries to conduct attacks on other resources.
In the process of analysing infected servers, researchers identified numerous websites and servers used by organisations in Russia, U.S., Europe, Asia and Latin America that the attackers had scanned with various tools, possibly to find a server that could be used to establish a foothold for hosting the attackers’ tools and to subsequently develop an attack. Some of the sites scanned may have been of interest to the attackers as candidates for waterhole. The range of websites and servers that captured the attention of the intruders is extensive. Kaspersky Lab researchers found that the attackers had scanned numerous websites of different types, including online stores and services, public organisations, NGOs, manufacturing, etc.
Also, experts found that the group used publicly available malicious tools, designed for analyzing servers, and for seeking out and collecting information. In addition, a modified sshd file with a preinstalled backdoor was discovered. This was used to replace the original file and could be authorised with a ‘master password’.
“Crouching Yeti is a notorious Russian-speaking group that has been active for many years and is still successfully targeting industrial organisations through watering hole attacks, among other techniques. Our findings show that the group compromised servers not only for establishing watering holes, but also for further scanning, and they actively used open-sourced tools that made it much harder to identify them afterwards,” said Vladimir Dashchenko, Head of Vulnerability Research Group at Kaspersky Lab ICS CERT.
“The group’s activities, such as initial data collection, the theft of authentication data, and the scanning of resources, are used to launch further attacks. The diversity of infected servers and scanned resources suggests the group may operate in the interests of the third parties,” he added.
Kaspersky Lab recommends that organisations implement a comprehensive framework against advanced threats comprising of dedicated security solutions for targeted attack detection and incident response, along with expert services and threat intelligence. As a part of Kaspersky Threat Management and Defense, our anti-targeted attack platform detects an attack at early stages by analysing suspicious network activity, while Kaspersky EDR brings improved endpoint visibility, investigation capabilities and response automation. These are enhanced with global threat intelligence and Kaspersky Lab’s expert services with specialisation in threat hunting and incident response.
More details on this recent Crouching Yeti activity can be found on the Kaspersky Lab ICS CERT website.