SEON has expanded its Signal Intelligence capabilities, growing its proprietary data foundation from more than 900 to over 1,100 directly sourced signals, as financial crime teams face a surge in AI-generated fake identities.
The new coverage spans address intelligence, session behaviour, phone and carrier data, and deeper digital footprint and device signals. The additions are designed to help risk teams identify inconsistencies within a customer’s identity and trace the infrastructure that links fraud rings together, without introducing extra friction into the customer journey.
Verifying genuine customers has become increasingly difficult. Where fraudsters once had to manually build identity evidence, complete forms and operate accounts one at a time, generative AI tools can now produce convincing profiles and consistent device histories within minutes.
The Financial Action Task Force has noted that anyone with a smartphone can create a convincing deepfake in roughly the time it takes to set up a social media account, while ACAMS research shows that three-quarters of anti-financial crime professionals have named GenAI misuse their leading emerging risk for a third year running.
The difficulty for fraud teams lies in the fact that individual data points can each appear legitimate in isolation, a valid email, a clean-looking device, a verified address, with fraud only becoming visible once those signals are cross-referenced.
SEON’s expanded signal set gives risk teams additional independent evidence across these layers, creating more opportunities to identify identity elements that have been fabricated, recycled or altered.
SEON positions itself as an AI Command Centre for fraud prevention and AML compliance, allowing risk and fraud teams to feed the new signals into rules, alerts, customer reviews and network investigations so that decisions are informed by a complete picture.
Every signal in the expansion can also be connected to an investigator’s preferred AI tools via SEON’s Model Context Protocol server, enabling AI agents to reason using real evidence gathered in one place. This is intended to let human analysts and AI agents draw on the same underlying signal base, carrying evidence from initial detection through to investigation and action.
The expansion strengthens three areas of identity assessment. On historical evidence, digital footprint checks now cover where an email or phone number has appeared across platforms including AI developer tools, job boards, property websites and dating apps, while new phone intelligence data adds SIM-swap and porting history, helping teams establish whether an identity predates the current transaction.
On infrastructure, address intelligence standardises and verifies addresses across more than 240 countries, assigning consistent identifiers that can reveal when separate accounts are linked to the same physical location through minor formatting differences, while expanded device intelligence can flag AI-agent activity, compromised iOS devices, Android eSIM mismatches and cases where a VPN disguises a device’s true network location.
On live behaviour, session monitoring tracks customers through onboarding, login, account recovery, checkout and payment, allowing teams to spot automation, remote access tools or off-screen activity while a session is still in progress.
SEON CEO and co-founder Tamas Kadar said, “AI has made a believable identity cheap to produce. What fraudsters cannot easily do at scale is build a consistent history for every account without reusing infrastructure. That is where our signal foundation makes the difference. The more dimensions a fraud team can check simultaneously, the harder it is to hide an identity that does not add up.”
Copyright © 2026 FinTech Global
