Incode Launches TrustGraph, a Trust Network to Detect Repeat and Agentic Fraud
In this press release, published on CyberTech Edition, Incode announces the launch of TrustGraph, a trust network built to detect repeat and agentic fraud across institutions. TrustGraph is the result of more than a decade of research by Incode and Identiq, which Incode acquired in June 2026. It uses secure multi-party computation, a cryptographic method, to compare one-time cryptographic data and find matching signals, so participating institutions never access one another’s customer records. The network connects institutions directly to each other, so there’s no central data store for attackers to breach. TrustGraph runs alongside the identity verification, onboarding, and authentication steps institutions already use.
Read the transcription of this press release, published by CyberTech Edition on October 14, 2026.
TrustGraph is a biometric-anchored, privacy-preserving trust network that helps financial institutions, marketplaces and AI companies detect repeat fraud and agentic fraud. In Incode’s early access program, it surfaced up to 53% more fraud than existing models alone.
San Francisco, October 14, 2026. Incode Technologies, the global leader in AI-powered identity verification and fraud prevention, today launched TrustGraph, the privacy-preserving trust network that enables institutions to detect repeat fraud and agentic fraud, as well as to recognize legitimate customers with signals from across the network, without pooling, exchanging or exposing customer data. In Incode’s early access program, institutions using TrustGraph detected up to 53% more fraud than with their existing models alone.
TrustGraph runs on patented peer-to-peer cryptographic technology that connects fraud and trust signals across participating institutions without creating a central pool of customer records. It is the product of more than a decade of research conducted by Incode and Identiq, a pioneer in cryptographic peer-to-peer identity validation founded by security, privacy and identity veterans. Identiq was acquired by Incode in June 2026.
Why now
Fraudsters can now use AI agents to build synthetic identities, forge documents, and retry after every rejection, targeting hundreds of companies at once. Incode projects that agentic fraud will account for 60% of all fraud attempts by the end of 2026. Today, individual institutions only see the attempts within their own systems, so one agent opening accounts at several banks in a single afternoon can look like a string of unrelated applicants.
Institutions have long understood that shared intelligence would help them combat fraud. However, institutions rarely share fraud information at scale because traditional approaches can require pooling or exchanging customer records, which can clash with privacy rules, create a single target for attackers, and risk exposing one institution’s customer data to another. As a result, repeat fraud patterns remain hidden.
TrustGraph changes that. Participating institutions, including direct competitors, can benefit from signals across the network without seeing one another’s customer records. Its cryptographic architecture is designed to protect the identities of institutions requesting and providing signals.
“Fraud is networked. Defenses are still siloed,” said Ricardo Amper, founder and CEO of Incode. “Attackers benefit from operating across institutions because each institution typically sees only its own interactions. A trust network changes that equation by turning isolated attempts into signals others can use. This is the trust infrastructure the AI era requires, and we’re proud to make it available today.”
What TrustGraph does
- Surfaces fraud no single institution can see. Anchored to verified biometric identities, TrustGraph recognizes repeat patterns across participating institutions, even when a bad actor uses a new name, document, or device, and returns a fraud signal in real time at onboarding, login, or a high-risk transaction.
- Exposes fraud rings. Within an institution’s own data, TrustGraph links seemingly unrelated applications that share a device, document details, or near-identical addresses, so investigators can treat the ring as one case.
- Detects fast-moving attacks, such as one device opening accounts at several banks in a single afternoon.
- Recognizes customers who have successfully verified elsewhere, providing a positive trust signal that can lower risk and help institutions accept more legitimate customers.
Why network intelligence matters
The value of a network approach extends beyond individual institutions. Interac, Canada’s payments and identity network connecting nearly 300 financial institutions, recognizes the importance of network intelligence in combating increasingly sophisticated fraud.
“How do you expect every single business to keep up with deepfakes, synthetic identities, and romance scams on its own? It is impossible. That is why we chose Incode, which has the strongest solution in the market today,” said Navjeet Grewal, Managing Director, Verification and Digital Credentials at Interac.
“TrustGraph allows institutions to benefit from fraud signals across the network without exposing customer data. 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,” Grewal added.
Privacy built into the architecture
- Customer records stay with the institution that holds them. TrustGraph uses privacy-preserving cryptography to match fraud and trust signals across participating institutions without pooling or exchanging customer records.
- Matches happen without exposing customer records. Secure multi-party computation (SMPC) compares one-time cryptographic material to identify matching signals without giving participating institutions access to one another’s customer records.
- There is no central pool of customer records to breach. The network is peer-to-peer, with no central data lake or data broker holding customer records for attackers to target.
TrustGraph provides the signal, and each institution makes the decision. Institutions apply their own rules to determine how to act on the signals they receive, ensuring TrustGraph serves as a source of intelligence, not a shared blacklist.