Wir möchten auf unserer Internetseite Dienste von Drittanbietern nutzen, die uns helfen, unser Werbeangebote zu verbessern (Marketing), die Nutzungsweise unserer Internetseite auszuwerten (Performance) und die Internetseite an Ihre Vorlieben anzupassen (Funktional). Für den Einsatz dieser Dienste benötigen wir Ihre Einwilligung, welche jederzeit widerrufen werden kann. Informationen zu den Diensten und eine Widerspruchsmöglichkeit finden Sie unter „Benutzerdefiniert“. Weitergehende Informationen finden Sie in unserer Datenschutzerklärung.
Our unique solution for online lending, gaming and other web-based businesses was developed to minimize fraud and credit risk. Clair uses behavioral profiling and biometrics to determine who your customers really are, to predict future business outcomes and fraud, and much more.
Leider gibt es für diesen Aussteller kein deutsches Firmenprofil.
ThreatMark AFS is the Full Stack Fraud Prevention and Seamless Authentication Service providing real-time recognition to differentiate legitimate customers and cybercriminals. AFS can detect traditional as well as modern threats that jeopardize online banking, transaction systems, and sensitive applications. Combination of evidence-based cyber threat detection capabilities and behavioral profiling including behavioral biometrics supported by machine learning makes a perfect fit for combating ever-changing threat landscape. The ability to recognize legitimate users improves detection capabilities and reduces false positives and manual reviews.
Nowadays, neither the traditional approach of rule-based transaction anomaly detection solution nor IP and browser-based user identification techniques is sufficient. These strategies are ineffective against today's attackers, using cunning identity-theft and social engineering-based techniques to bypass all protective measures. Traditional solutions don’t have enough relevant nor detailed data to be effective in detecting modern attacks. Moreover, the lack of detailed information and context results in a high number of false-positive detections that need to undergo costly manual reviews.
To decrease the number of false positives, our Anti-Fraud Solution (AFS) focuses on context and offers a layered approach to protection. At each stage of user interaction with the protected application, security checks are applied to detect differences in assumed identity. If the current profile differs from the learned model by the certain customizable threshold, an alert is raised. This unique approach allows AFS to detect traditional as well as modern threats that jeopardize online banking, transaction systems, and sensitive applications.
The AFS is a full-stack fraud detection system based on modern cognitive security user-centric approach. Combination of evidence-based cyber threat detection capabilities and deep behavioral profiling including behavioral biometrics supported by machine learning makes a perfect fit for combating ever-changing threat landscape. The ability to recognize legitimate users and fraudsters based on their behavior does not only improve detection capabilities but also reduces false positives and manual reviews.
Also, the solution is modular and can work with certain data only if necessary or if other solutions are in place to take care of the analysis of such data. Quite often AFS is deployed as threat detection and user identity verification solution together with third party transaction monitoring solution. Such solutions can work together if needed to fully benefit from each other.
AFS provides comprehensive online management summary of the protected system, displaying overall risk level, recently detected incidents, providing various trends such as the number of detections, number of users endangered along with lists defining most dangerous devices and IP addresses. The interface also provides very detailed information for every monitored entity as a user, device, session or transaction, such as user actions timeline, previously used devices along with the device fingerprint and so on. Each entity is linked with risk score which is then combined into an overall score of the user interaction with the protected system.