German Government Uses Quantum for Fraud Detection, Data Privacy

Multiverse Computing and the German federal government’s technology company Bundesdruckerei have partnered to explore quantum and quantum-inspired solutions for enhanced data privacy and fraud detection.

The partners recently completed two research projects that combined quantum-inspired software and data security expertise to build new prototypes that generate synthetic data more accurately than classic standard algorithms for machine learning.

The team investigated use cases for the technology including improving the privacy and effectiveness of synthetic data generation and detecting fraudulent transactions in blockchain networks.

The companies used quantum-inspired machine learning, a cutting-edge approach that applies quantum theoretical principles such as tensor networks to optimize data management and machine learning tasks. These methods offer scalability, efficiency and precision, compressing and processing large datasets without sacrificing critical information.

Advanced Synthetic Data Generation

The first project aimed to enhance the generation of synthetic data—a critical tool for machine learning and AI—while ensuring robust privacy protections. Synthetic data serves as a substitute for real datasets, enabling scalable and secure AI model training while mitigating risks such as data bias and privacy violations.

Related:IBM Launches Its Most Powerful Quantum Computer

Using a publicly available dataset, the teams developed a quantum-inspired AI model that integrated differential privacy as an additional layer of protection. This innovation could ensure that individual entries in a dataset cannot be reverse-engineered, safeguarding against internal and external adversarial attacks.

Compared to generative adversarial networks (GANs), a standard classical algorithm for synthetic data generation, the quantum-inspired model outperformed its classical counterpart, achieving 15% higher accuracy in generating synthetic data closely resembling the original dataset.

“There’s no doubt that we will continue to see new ways that quantum solutions can make AI stronger and more efficient in the service of protecting people and data,” said Multiverse Computing CEO Enrique Lizaso Olmos

“Our work with the team at Bundesdruckerei shows how to combine expertise of each technology leader to explore the new generations of AI solutions by leveraging quantum and quantum-inspired computing to raise the level of data privacy and cyber security.”

Enhancing Blockchain Fraud Detection

The second project addressed fraud detection within blockchain networks. Using a combination of a quantum-inspired graph neural network and a quantum-boosting machine learning algorithm, the team developed an AI solution to identify fraudulent transactions.

This novel approach demonstrated significant improvements in efficiency, achieving performance on par with classical algorithms while reducing AI model parameters, resulting in an 11% improvement in training time and a 27% reduction in inference time.

“The research cooperation with Multiverse Computing is a great addition to our research activities in the field of quantum technologies. It is very important for us to work together with the leading quantum industry players to explore new AI solutions in the quantum age, in particular in the context of data privacy and cyber security,” said Bundesdruckerei head of innovations Kim Nguyen.