Using AI automation to bolster private network and critical infrastructure security
- The increasingly networked world is a dangerous place, with criminals turning to AI and Quantum Computing to confound our defenses
- And, as recent events proved the criminals have been having some successes
- The ADVA-led AI-NET-PROTECT project aims to tip the balance back in favour of the good guys
ADVA is to lead the European project, AI-NET-PROTECT, which aims to use AI-based automation to build a security framework for private networks and critical infrastructure in Europe.
Front of mind is the danger that quantum technology already poses to the encrypted keys, which form the basis of organised network and system security. Simply stated, the problem is that just as the industry as a whole has turned to ‘openness’ as a means of advancing the technology, many global users have resorted to increasing the pace of digitalisation as a means of coping with the pandemic, says Achim Autenrieth, director of advanced technology in ADVA’s CTO team.
As a result there’s been a huge rise in online activity - banking, retailing, conferencing and, of course, home working; and a rise of network complexity to go with it, he explains. The result is a fast-growing attack surface that can, and is, being exploited by aggressors who are now starting to use AI and quantum computing technology to find the cracks in corporate security.
It goes without saying that security breaches can be devastating and may even put the survival of huge companies at risk, as T-Mobile in the US has found out as it braces itself for a class action onslaught in the wake of a huge personal data breach (see today’s TelecomTV What’s up with... T-Mobile).
European industry has a good position in 5G networks, transportation and industrial applications, says the project abstract, but it needs to strengthen its position in secure cloud, data centre and artificial intelligence technologies to be at the forefront of development.
So the AI-NET-PROTECT project is to right the balance by providing automated resilience and secure networks operated on trusted equipment to critical infrastructures and enterprises. Its goal is to ensure the protection of critical data, network performance (like latency, throughput, availability), and infrastructure (against tampering and attacks).
To get there, the project aims to develop a scalable network and node architecture to address the diverse KPIs by a mix of open and purpose-built hardware and software including whiteboxes. Network telemetry and intent-based software-defined network management and control will provide zero-touch provisioning and support artificial intelligence based automation of end-to-end services. Strong security based on multi-layer cryptography, agile crypto-functions, and quantum-safe algorithms will form an integral part for the developed architecture. The key use cases for AI are performance optimization, proactive fault and anomaly detection, penetration and vulnerability testing, and security incident management.
Anomaly detection is a key element. “We have to collect data and we have to find anomalies in it to move forward,” Achim Autenrieth explains. “You monitor the network over a period of time and then anomalies can be detected and you can train the system to recognise them when they occur again as part of an attack. Over the longer term, moving to small-to-medium-sized data centres, sited closer to the users will be a step forward security-wise as there will need to be local AI decisions,” he says.
“As the leader of AI-NET-PROTECT, we’re helping to lay the foundations for tomorrow’s intelligent and secure enterprise and government networks. Together with our partners across four countries, we’re creating solutions that harness automation and rapid threat detection for new levels of resilience and data protection,” says Christoph Glingener. ”The AI-NET-PROTECT project will help improve our open networking technology, including our FSP 3000 open line system and our TeraFlex terminal, as well as our ConnectGuard encryption solution and our pioneering work driving quantum-resistant communications technology.”
AI-NET-PROTECT is one of three sub-projects of the ‘Accelerating Digital Transformation in Europe with Intelligent Network Automation’ (AI-NET) initiative. Also coordinated by ADVA, the flagship CELTIC-NEXT project is a €74-million public-private partnership bringing together major players from across the industry. Running until August 2024, it aims to tackle increasing complexity by shifting cloud infrastructure from its current centralized model towards edge-centric computing using 5G and AI. As well as developing tools to give end customers access to more agility, functionality and scale, AI-NET will address global supply chain challenges and promote sustainable growth in Europe.
Stay up to date with the latest industry developments: sign up to receive TelecomTV's top news and videos plus exclusive subscriber-only content direct to your inbox – including our daily news briefing and weekly wrap.