Fraud Intelligence Lab

Fraud rarely announces itself clearly. More often, it appears as a pattern, anomaly or connection hidden among thousands—or millions—of legitimate activities. Fraud investigators have always relied on information to identify suspicious behaviour. What has changed is the volume of data now available and the speed at which it can be analysed. Payments, account activity, devices, locations, login behaviour, customer records and relationships between individuals or businesses can all produce signals that may help identify fraud. This is where fraud analytics becomes important. Fraud analytics uses data-analysis techniques to identify patterns, anomalies, relationships and behaviours that may indicate fraudulent activity. It can help organisations move from simply reacting to reported fraud towards identifying suspicious activity earlier. But analytics does not magically determine whether someone has committed fraud. A suspicious transaction is not the same thing as a fraudulent trans...

Fraud investigations increasingly begin with a simple question: what can be discovered from information that is already publicly available? Websites, company records, social media, news reports, online marketplaces, images, maps and other public sources can all provide useful pieces of information. When those pieces are collected, evaluated and analysed systematically, they can contribute to what is commonly known as open-source intelligence, or OSINT. OSINT can help investigators identify connections between people, companies, addresses, websites and other entities. It can also help corroborate information, identify new lines of enquiry and build a clearer picture of how suspected fraud operates. But OSINT is not simply searching Google or looking through someone's social-media profile. The intelligence comes from how information is collected, evaluated, connected and verified. OSINT combines publicly available information from multiple sources to identify connections, corrobor...

  Artificial intelligence is changing the economics of fraud. Many scams still rely on familiar techniques: impersonation, social engineering, urgency, deception and the exploitation of trust. What is changing is the technology available to criminals. Generative artificial intelligence can produce convincing text, images, audio and video at speed. It can help criminals imitate trusted individuals, create synthetic identities, improve fraudulent communications and potentially operate some scams at greater scale. The UK's National Assessment Centre has assessed that criminals will increasingly adopt generative AI technologies such as deepfakes, large language models and voice cloning to enable fraud. Importantly, the technology is currently being used largely to enhance existing fraud threats rather than invent completely new categories of fraud . That distinction matters. The fundamental psychology of many scams remains familiar. AI can simply make the deception more convincing...

 Fraud is changing rapidly. Traditional fraud schemes have not disappeared, but they are increasingly being combined with digital technologies, large-scale data collection, automation and artificial intelligence. Criminals can operate across borders, impersonate legitimate organisations, manipulate victims through social engineering and exploit digital financial systems at considerable speed. At the same time, investigators and organisations have access to increasingly sophisticated tools for identifying suspicious behaviour. This is where fraud intelligence becomes important. AI, data analytics and network analysis are increasingly used to identify suspicious activity and support fraud investigations. What is fraud intelligence? Fraud intelligence is the process of collecting, analysing and interpreting information to understand fraud threats, identify suspicious activity and support decisions about prevention, detection and investigation. It goes beyond simply identifying an indi...