Synthetic identities, a growing menace in recent years, blend genuine and falsified information to deceive identity verification systems. These fabricated personas are meticulously crafted from stolen Social Security numbers, inaccurate names, and fictitious contact details, posing a significant challenge to security measures.
In the battle against synthetic identities, companies like TransUnion are adopting a detective-like approach by delving into public data for crucial clues. Recent research highlights key traits and behavioral patterns that can help unmask these deceptive identities. For instance, synthetic identities often lack typical markers such as familial connections, vehicle registrations, voter records, or bankruptcies.
At the forefront of this investigative process is TransUnion’s Synthetic Fraud Model, which boasts an impressive 85.6% accuracy rate in predicting fraudulent activities. While certain living characteristics can aid in identifying synthetic identities, they are just pieces of a larger identity puzzle, as explained by Steve Yin, TransUnion’s senior vice president and global head of fraud.
To deal with the remaining 14.4% of suspected synthetic identities that are genuine individuals, additional authentication measures are employed. This multi-layered approach combines automated decision-making with manual reviews by fraud specialists, ensuring a comprehensive verification process, as detailed by Brad Daughdrill, TransUnion’s vice president of Data Science.
TransUnion initially introduced the Gramm-Leach-Bliley Act (GLBA) Synthetic Fraud Model in 2021, which scrutinizes Personally Identifiable Information (PII) for inconsistencies indicative of synthetic identities. Over time, the model has evolved through advanced technologies like AI and machine learning, bolstered by enhanced infrastructure for quicker updates and more efficient analysis.
Despite these advancements, fraudsters behind synthetic identities remain elusive and adaptive. Their methods vary widely, making it challenging to establish a definitive model for detecting fake personas. These perpetrators often establish false credibility by building credit histories gradually, only to exploit their access for substantial gains before disappearing without a trace.
Synthetic identity risks are exacerbated by extensive data breaches, with 640 million consumer records compromised in a single year, exposing sensitive information like Social Security numbers. This breach severity is a strong predictor of future fraud activities, underscoring the urgent need for proactive measures to combat synthetic identity threats.
TransUnion’s analysis reveals that a significant portion of financial services customers exhibiting high synthetic identity risk scores had defaulted on loans and credit card accounts, despite passing standard identity verification checks. This discrepancy highlights the insidious nature of synthetic fraud and the importance of ongoing vigilance in identity validation processes.
To mitigate synthetic identity risks effectively, organizations are advised to adopt a holistic approach to identity validation, integrating continuous assessments throughout a customer’s lifecycle rather than relying on one-time verifications. By implementing enhanced fraud detection models, fostering transparency in vendor partnerships, and consolidating fraud intelligence resources, businesses can fortify their defenses against evolving fraud tactics.
Takeaways:
– Synthetic identities blend genuine and falsified information to deceive verification systems.
– Advanced technologies like AI and machine learning are instrumental in detecting synthetic fraud.
– Ongoing vigilance and continuous assessments are crucial in combating synthetic identity risks.
– Transparency in vendor partnerships and centralized fraud intelligence hubs enhance fraud prevention strategies.
Tags: automation
Read more on biometricupdate.com