As network attacks get more sophisticated, AI can help with threat detection
As it continues to develop, 5G will become increasingly complex. The need to deploy virtualized, programmable infrastructure becomes more pressing as new bandwidth-consuming enterprise, industrial and consumer applications hit the market. And, in the long run, the vision of 5G contemplates advanced analytics and artificial intelligence (AI) automating network operations and resource allocations.
Across the vendor ecosystem, products with built in AI are hitting the market. Mavenir, for instance, recently released a network security and fraud management software suite that uses machine learning and deep learning to enable real-time threat detection and analysis. Network signaling is a major threat vector on which Mavenir is focused.
Location tracking, interception of voice and text messages, denial of service and account fraud are all potential attack vectors associated with the Signaling System 7 (SS7) protocol. And those same vulnerabilities can be applied to diameter signaling, according to a report from the FCC’s Communications Security, Reliability and Interoperability Council (CSRIC).
SS7 is the signaling protocol for 3G networks while diameter signaling is used to route traffic in an LTE or IP network. In an interview with RCR Wireless News, Oracle Director of Cybersecurity for Service Provider Networks Travis Russell, also a CSRIC member and author of the report, said bad actors are becoming increasingly interested in exploiting diameter signaling.
“There have been breaches on SS7,” Russell said. “It’s the same use cases and same vulnerabilities in SS7 that we reported on diameter. In diameter, it’s a bit different because most all of the networks are still using SS7 to connect and not the diameter protocol. We wouldn’t expect to see a lot of activity on diameter yet.” Network operators “are saying that in some cases they are seeing some probing, but it’s hard to really substantiate what that is.”
Based on his work with Oracle and with the FCC, Russell said service providers are concerned about the security “on the interconnect. Everybody has come to the realization that this is serious stuff. There’s a lot of work going on to secure the signaling network. We’re seeing a lot of activity and requests from customers to add more security capabilities for diameter.”
Mavenir CEO Pardeep Kohli said fraud activity represents a multi-billion source of revenue loss for communications service providers. “Malicious attacks are evolving with technology at a rapid pace and take revenue from operators. Without sophisticated, adaptable, and self-learning security solutions, operators will forever be behind the technology curve with unprotected revenues. We provide advanced cloud-native security for every type of messaging and signaling protocol used in the telecom environment with anti-spam, anti-fraud solutions and firewall products.”
Beyond just security, AI will be key to all areas of network operations, according to Ben Parker, chief technology officer of Guavus. “As CSPs prepare for 5G, the ones who will to be successful over the long term will focus on introducing advanced network operations and customer experience systems into the network. The increased number of network elements, coupled with the increased number of devices connected, will make it nearly impossible to run a 5G network without the assistance of AI-driven analytics.”
