EU-funded researchers are building a services development platform that, once complete, could combat credit card fraud, mobile telephone SIM card cloning and even fraudulent unpaid telephone calls in real time. The breakthrough is possible via a technological advance that would significantly increase the current speed of data processing.
The platform is being built as part of the STREAM (‘Scalable autonomic streaming middleware for real-time processing of massive data flows’) project, which has been partially funded with EUR 2.6 million from the ‘Information and communication technology’ Theme of the Seventh Framework Programme (FP7). The project’s aim is to build a scalable technology for real-time processing of massive data flows.
Banks, payment processors and other companies dealing with credit card payments have a variety of systems and safeguards to protect against fraudulent credit card use. These range from matching signatures electronically to blocking a card number after it has been reported stolen. There is often a delay, though, between reporting a card as lost and its cancellation taking effect.
This delay is due to computing applications which require strong analysis and processing capabilities. People using stolen cards often know about this time gap, and try to make purchases soon after a card is stolen.
The platform developed by STREAM would eliminate this delay by implementing a scaling system that makes use of large node clusters, or stand-alone servers, to process massive data throughput on an order of millions of data per second. This massive increase over current processing rates would allow real-time processing of information flows and provide unsupervised and autonomous operation. This change, say the project organisers, will allow for broader deployment of data-processing products and services to new areas that need to manipulate large information flows in a cost-effective manner.
Like credit card providers, telecom companies have to block numbers after a mobile phone is stolen. The cloning of SIM cards is a great concern to security and police services since it renders location-based services (LBS) unreliable when more than one handset uses the same SIM. At present, the use of cloned cards and stolen phones is only detected after the fact and is subject to the same kind of delay as credit cards.
The STREAM platform is related to cloud computing initiatives. Cloud computing typically involves the provision of scalable and often virtualised resources as a service over the Internet. STREAM is designed for deployment in a cloud computing environment, with features like elasticity and scalability. The technology can automatically increase or decrease the number of nodes according to the computational requirements at any given time. This type of organisation helps reduce costs while eliminating single points of failure.
Other areas of use for the STREAM platform include the Internet protocol (IP) traffic of an organisation, the output of a large sensor network, e-mail processed by an Internet service provider and market feeds from a stock exchange or financial markets.
The School of Computing in Spain’s Technical University of Madrid is responsible for developing the scalable data flow processor, which is STREAM’s hard core. To do this, it parallelises the query operators, and can deploy each operator on a 100-node cluster. This multiplies the processable data throughput a hundredfold. The processing capacity of current single-node technologies is now two orders of magnitude lower than what STREAM’s will be.
Other research partners, apart from UPM, are Telefónica, a Spanish telecoms provider, and Exodus, a subsidiary of Piraeus Bank, based in Greece. The former will employ STREAM in an antifraud system for mobile telephony, while the latter will apply the project results to its credit card payment antifraud systems.
