Device Fingerprint Risk Scoring for Bot-Resistant Sign-In
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Malicious users attempt to access user accounts by tricking the system into authenticating them using bots, which automate the sign-in process, leading to threats like Account Takeover (ATO).
Innovation Solution
A system that analyzes sign-in requests for fingerprints, generates a risk score based on attributes like IP address, user agent, and user interaction, and issues challenges or suspensions if the score exceeds a threshold to thwart bot activity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional authentication methods are used, then ease of operation is maintained, but the system becomes vulnerable to bot-based attacks
Solution Approach 1:
The patent introduces an intermediary risk scoring system that sits between the user's sign-in request and the authentication decision. This mediator analyzes device fingerprints, behavioral attributes, and request patterns to generate a risk score, which then determines whether additional verification steps are needed. This resolves the contradiction by automatically adding friction only when necessary, rather than requiring all users to go through complex verification processes.
Solution Approach 2:
The system dynamically changes the authentication parameters based on the calculated risk score. For low-risk requests, the system maintains simple password-based authentication. For high-risk requests, it automatically adjusts the parameters to require additional verification steps such as device binding confirmation, CAPTCHA challenges, or multi-factor authentication. This parameter adaptation allows the system to maintain ease of operation for legitimate users while enhancing security for suspicious activities.
2Measurement precision
If bot detection analysis is performed on all sign-in requests, then detection precision is improved, but processing time increases
Solution Approach 1:
The patent implements partial action by applying bot detection analysis selectively rather than universally. The system performs lightweight initial filtering on all requests, then applies comprehensive fingerprint analysis and attribute comparison only to requests that exceed certain thresholds or exhibit suspicious patterns. This partial application of detection measures maintains high detection precision for problematic requests while avoiding the time penalty of analyzing every single sign-in attempt.
Solution Approach 2:
The system applies different levels of detection quality to different requests based on their characteristics. High-risk requests receive full-spectrum analysis including device fingerprinting, behavioral attribute monitoring, and correlation with known bot patterns. Low-risk requests from recognized devices or locations receive streamlined verification. This local differentiation of detection quality optimizes the balance between detection precision and processing time.
Data Source
AI summary
A method includes receiving information indicative of a sign-in request associated with an account registered on a service; determining whether the sign-in request comprises a fingerprint, wherein the fingerprint comprises one or more attributes associated with an interaction of a user during a sign-in on the account; dynamically generating a risk score based on a comparison of the one or more attributes of the fingerprint with one or more attributes of a set of attributes collected from a plurality of sign-in requests, wherein the risk score is based on a determination that the fingerprint correlates with attributes in a set of attributes identified as associated with behavior associated with a bot; and in response to the risk score being at or above a risk score threshold, issuing an indication of failure of the sign-in request.