Topic starter
12/07/2026 12:26 pm
TL;DR: Fraud prevention has moved beyond rules-based systems toward machine learning, real-time trust decisions, and more prescriptive customer guidance as AI reshapes the threat landscape, according to Sift. The identity and access lesson is clear: static controls cannot keep pace with dynamic abuse, especially where account trust, session behaviour, and friction all need to be decided in context.
Editorial analysis by NHI Mgmt Group, based on content published by Sift: “15 Years of Sift: Jason Tan and Marc Friend on Fraud, Trust, and What Comes Next”.
Key questions
Q: What breaks when fraud controls stay rules-based in fast-changing abuse environments?
A: Rules-based fraud controls become brittle when attackers can study thresholds, automate around them, and shift behaviour faster than analysts can update exceptions.
Q: Why do adaptive trust models change the way security teams think about customer friction?
A: Because friction becomes a policy decision rather than a static checkout setting.
Q: What are the signs that a fraud operation is no longer keeping pace with changing attack patterns?
A: Common warning signs include analysts re-evaluating their tools, rising fraud rates, increasing manual workload, and model updates that lag behind attacker behavior.
Practitioner guidance
- Define trust tiers for customer sessions Map transaction and session signals to explicit trust levels so that friction changes are governed by policy rather than ad hoc analyst judgment.
- Document override criteria for adaptive decisions Require clear human review standards for cases where the model recommends challenge removal, step-up verification, or account restriction.
- Join fraud and identity telemetry Correlate account history, device reputation, and authentication behaviour so the same user is treated consistently across checkout and access flows.
Bottom line: Fraud prevention is moving toward adaptive decisioning because static rules cannot keep pace with changing abuse and customer expectations.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
12/07/2026 12:39 pm
Adaptive trust is becoming a governance layer, not just a fraud feature. Once decisions about friction, challenge, and trust are made in real time, they start functioning like access control decisions. That makes auditability, policy ownership, and feedback loops matters for both fraud teams and identity programmes. The practitioner conclusion is that trust policy now needs the same discipline as entitlement policy.
A few things that frame the scale:
- Nearly 60% of companies reported that fraud losses were still increasing in 2025.
A question worth separating out:
Q: How should fraud, identity, and product teams share accountability for trust decisions?
A: Accountability should be shared across fraud, identity, product, and operational leaders, because trust decisions affect conversion, risk, and customer experience at the same time. Each team should own a defined part of the control chain, from policy design to customer impact measurement. Clear ownership reduces gaps where onboarding, authentication, and fraud review can fail separately.
👉 Read our full editorial: Fraud trust models are shifting from rules to adaptive decisioning