Could quantum computers spot fraud before your bank does?
Quantum computers may soon give banks and cybersecurity teams a powerful new ally in the fight against fraud.
New research using IBM quantum hardware has shown that quantum algorithms can detect subtle anomalies in complex datasets faster than classical systems – a key step toward catching fraudulent transactions, irregular trading, or cyber intrusions before they spread.
The study, carried out by quantum software startup Haiqu and run on an IBM Quantum Heron processor, demonstrated that “quantum embeddings” – ways of encoding classical data for quantum analysis – can process hundreds or even thousands of data features at once.
Anomaly detection
The results, detailed in a Haiqu blog, are anomaly detection models that operate faster and potentially more precisely than their classical counterparts. This approach targets one of the biggest challenges in fraud detection: scaling analysis across millions of data points while reducing false positives.
In sectors like finance, healthcare, and logistics, these small accuracy gains can mean catching a rogue transaction or hidden breach before damage occurs.
The Bank of Montreal (BMO), North America’s eighth-largest lender with a market value of around $30 billion, joined IBM’s Quantum Network earlier this year to explore how emerging quantum tools could enhance fraud prevention and portfolio modeling.
The bank’s chief AI and data officer, Kristin Milchanowski, said the research marked a genuine shift in what quantum technology could mean for financial AI.
“This innovation doesn’t just advance research; it accelerates the shift toward real-world impact in industries like finance, where precision and insight redefine what’s possible.”
IBM’s own researchers say the results are an encouraging sign that quantum advantage – the moment when a quantum system outperforms any classical computer at a useful task – may be within reach.
Quantum advantage
“The ability to encode high-dimensional data with hundreds and even thousands of features enables applications of a new scale, as what the team at Haiqu has experimentally shown on our hardware,” said Jay Gambetta, director of IBM Research.
“Advances like this are what push the industry towards achieving a quantum advantage in the near term,” he added,
Professor Oleksandr Kyriienko, chair in Quantum Technologies at the University of Sheffield and a leading expert on QML, said the progress was both technically significant and practically relevant.
Have thoughts about this topic? Others do, too. Join them in the discussion.
“Anomaly detection is a very suitable target, since even a smaller improvement in scores can lead to crucial detections or elimination of false positives.”
While the study stops short of declaring full quantum advantage, the team working on the study claims that it offers the strongest signal yet that quantum processors can enhance fraud detection and cybersecurity workflows.
The news comes in the same week that IBM launched two new quantum processors, named “Loon” and “Nighthawk,” with the goal of achieving error-free computing and substantiating existing research.
Unlock more exclusive Cybernews content on YouTube.
