Visa DPS Unveils AI-Powered Fraud Defense Focused on Behavioral Signals, Shifting from Reactive to Proactive Security
SAN FRANCISCO – September 12, 2024 – Visa DPS is bolstering fraud prevention strategies with a new approach centered on analyzing behavioral biometrics and device telemetry before transactions occur, the company announced today. This shift, driven by artificial intelligence, aims to identify and neutralize threats earlier in the customer journey, moving beyond traditional, transaction-based fraud detection.
The new system integrates bureau checks with Visa’s internal threat intelligence and behavioral signals collected over time, creating a unified fraud intelligence layer. This allows for the connection of disparate data points into a single, actionable view, according to Visa DPS representatives.
“You can learn a lot by understanding how someone holds their phone and types,” explained Visa DPS’s head of strategy, [Name not explicitly stated in text, referred to as “White” throughout]. “If a consumer historically logs in with one hand at a slow cadence, and suddenly a session appears using two hands at rapid speed, that’s a signal.If a consumer who never wires money suddenly initiates a transfer while on an active phone call, that too is a red flag.”
The focus on mobile and login “touchpoints” is especially valuable due to the rich behavioral data they provide. This allows Visa DPS to gather insights - such as typing speed and grip - before a transaction is even initiated. The system can also flag anomalies like unexpected email address changes,differentiating between legitimate updates (like household consolidation of receipts) and malicious activity designed to suppress fraud alerts.
“If a fraudster compromises an account, swaps an email so that I’m no longer getting alerts … we can stitch that activity together, say, OK, email was changed from email A to email B, how risky is email B based on past history that we’ve seen across the network?” White stated.
This proactive strategy, described as “upstream” on the fraud timeline, represents a move towards “holistic risk management across any interaction that you have with your customer, member or cardholder,” rather than solely reacting to fraudulent transactions.
Looking ahead, Visa DPS emphasizes the need for stronger authentication, improved customer education, and continued investment in AI-powered analysis. However, the company stresses that effective fraud detection requires a collaborative effort.
“Fraud detection must be an organizational endeavor, and not just something that the back-office team or the fraud card team works on,” White said. He highlighted that attacks frequently originate in one division – such as loyalty programs, auto lending, or personal loans – and then spread. Data sharing both internally and between financial institutions is thus critical.
Ultimately, Visa DPS believes “identity intelligence will be the backbone of next-gen fraud prevention,” as fraudsters continue to evolve their tactics. The company is positioning itself to anticipate and defend against these increasingly sophisticated attacks.
