Identity verification company Incode has launched TrustGraph, a network that lets banks and other businesses spot fraudsters who have targeted other members, without sharing their customers’ records with each other. Incode announced it on 14 October 2026.
The problem it targets
Incode says fraudsters can now use AI agents to create fake identities, forge documents and target hundreds of companies at once. Because each company sees only the attempts made against it, one attacker hitting several banks in an afternoon can look like many unrelated applicants. Incode “projects that agentic fraud will account for 60% of all fraud attempts by the end of 2026.” That is the company’s own forecast.
“Fraud is networked. Defenses are still siloed,” said Ricardo Amper, Incode’s founder and CEO.
How it works
According to Incode, TrustGraph is “anchored to verified biometric identities” and spots repeat patterns across members even when a fraudster uses a new name, document or device. It sends a warning signal in real time when someone signs up, logs in or makes a high-risk transaction. It can also flag customers who have already been verified elsewhere.
Incode says the network uses secure multi-party computation (SMPC), a cryptographic method that “compares one-time cryptographic material to identify matching signals without giving participating institutions access to one another’s customer records.” There is no central database of customer records, and each institution decides for itself how to act on a signal. The technology builds on work by Identiq, which Incode bought in June 2026.
Incode says that in its early access programme, “institutions using TrustGraph detected up to 53% more fraud than with their existing models alone.” This is Incode’s own figure and has not been independently checked.
A customer’s view
Navjeet Grewal, managing director of verification and digital credentials at Interac, Canada’s payments and identity network, said: “How do you expect every single business to keep up with deepfakes, synthetic identities, and romance scams on its own? It is impossible.” He added: “If Company A experiences an attack and the same actor later targets Company B, Company B doesn’t have to face that attack as if it were the first time.”
TrustGraph is available now as part of the Incode platform.
What this means
- Fraud fighters can team up. Firms can learn from attacks on others without swapping customer data.
- AI-driven fraud is the target. Incode is pitching it against fraud run by AI agents.
- The numbers are Incode’s. Its 53% and 60% figures have not been independently tested.
Sources
- Incode, “Incode launches TrustGraph, the first trust network built for the agentic era”, Business Wire press release, 14 October 2026, via AFP. https://www.afp.com/en/infos/incode-launches-trustgraph-first-trust-network-built-agentic-era
