Advancing UK Aerospace, Defence, Security & Space Solutions Worldwide
  • Home
  • /
  • Defence
  • /
  • BAE Systems develops machine learning to advance cyber techniques for DARPA’s CSL

Defence Security

BAE Systems develops machine learning to advance cyber techniques for DARPA’s CSL

BAE Systems’ FAST Labs research and development organisation has been tasked by the Defense Advanced Research Projects Agency (DARPA) to develop a scalable machine learning system designed to provide data anonymity to improve data sharing for its Cooperative Secure Learning (CSL) programme, which has many potential applications, including cybersecurity.

Image courtesy BAE Systems / copyright Shutterstock

Security Operations Centres (SOC) function at the forefront of machine learning technology as they work to identify emerging cyber threats by analysing large volumes of data. Yet, standard security log data fields such as IP addresses and URLs reveal sensitive details about their internal infrastructure and services that adversaries can use to craft attacks. This leads to limited information sharing among SOCs, resulting in a situation of many SOCs having only pieces of the cyber threat landscape puzzle.

Advertisement
Teledyne

To advance research in this area, DARPA asked BAE Systems to develop a scalable machine learning solution that preserves the privacy of the data and the model, enabling Cooperative Secure Learning. By sharing information – while keeping the actual data secure – individual puzzle pieces can be connected to build the complete picture, enabling new cybersecurity models and protections to be created.

“The challenge was immense but very straightforward – to create a system of information sharing for advanced research and security modelling in a way that preserves the security of the data,” said Bernard McShea, principal investigator at BAE Systems’ FAST Labs. “Our approach allowed us to leverage the organization’s extensive experience in machine learning, security and success on previous DARPA programmes.”

BAE Systems' Privacy-preserving Arithmetic Computation for Encrypted Learning solution, known as PArCEL solution, overcomes common privacy challenges by combining the company's recent research in cooperative learning on encrypted feature embeddings with new network log sanitisation techniques. Unlike other approaches such as encryption of raw private data, BAE Systems' focus on feature embeddings reduces computational complexity while providing additional protection against information leakage and reduced information sharing.

Advertisement
Gulfstream RT

Work on this approximately $1 million programme, which includes research teammates led by Prof. Khorrami at New York University, builds on BAE Systems’ previous work in cyber hunting, automated defence of cyber dataset, machine learning, and related techniques.

 

Advertisement
PTC PTC
UKI2S backs Cryogenx to tackle military heat stress

Defence

UKI2S backs Cryogenx to tackle military heat stress

15 July 2025

The UK Innovation & Science Seed Fund (UKI2S), managed by Future Planet Capital, has invested £430,000 in Cryogenx as part of a £1.7 million seed funding round to accelerate development of its breakthrough portable cooling technology.

RTX

Defence

RTX's Raytheon awarded US Navy RAM GMLS contract

15 July 2025

RTX's Raytheon has been awarded a $74 million contract to produce RAM Guided Missile Launching Systems (GMLS) for the US Navy.

Lane Electronics to showcase connectivity solutions at DSEI 2025

Defence Security Events

Lane Electronics to showcase connectivity solutions at DSEI 2025

15 July 2025

Franchised distributor of electrical, electronic and optical connectors, Lane Electronics, will be exhibiting at DSEI 2025 (9th–12th September 2025, Excel London) will have the opportunity to explore the company’s latest connector technologies and its UK-based assembly and services.

Galvion to supply 5,000 more Batlskin Caiman helmets to Canadian DND

Defence

Galvion to supply 5,000 more Batlskin Caiman helmets to Canadian DND

15 July 2025

Galvion has received a second follow-on order from the Department of National Defence (DND) Canada for its flagship Batlskin Caiman ballistic helmet systems.

Advertisement
ODU RT
Systematic launches SitaWare BattleCloud

Defence

Systematic launches SitaWare BattleCloud

15 July 2025

C4ISR solutions developer Systematic, today announced the launch of SitaWare BattleCloud — a cloud-native evolution of the proven SitaWare Suite — alongside new features for the SitaWare suite.

BAE Systems

Defence

BAE Systems' Leadership Academy opens in Barrow

14 July 2025

BAE Systems has opened a new Leadership Academy in Barrow to deliver world-class educational facilities for designing and building Royal Navy submarines.

Advertisement
Teledyne