18097738. SCREEN-ANALYSIS BASED DEVICE SECURITY simplified abstract (Google LLC)
Contents
SCREEN-ANALYSIS BASED DEVICE SECURITY
Organization Name
Inventor(s)
Matthew Sharifi of Kilchberg (CH)
Kai Wang of Santa Monica CA (US)
David Petrou of Brooklyn NY (US)
SCREEN-ANALYSIS BASED DEVICE SECURITY - A simplified explanation of the abstract
This abstract first appeared for US patent application 18097738 titled 'SCREEN-ANALYSIS BASED DEVICE SECURITY
Simplified Explanation
The patent application describes a system and method for content-based security on computing devices. Here are the key points:
- The system identifies the content being rendered by a mobile application during a session.
- It generates feature vectors from the content and compares them to a classification model.
- If the feature vectors do not match the model, a challenge is provided to authenticate the user of the mobile device.
- The system can also determine if the device is located at a trusted location.
- It captures information from the session and generates feature vectors for training.
- The system repeats this process until a training criteria is met.
- It then trains a classification model using the feature vectors and authenticates the user using the trained model.
Potential applications of this technology:
- Enhancing security on mobile devices by authenticating users based on the content being rendered.
- Preventing unauthorized access to sensitive information by challenging users when the content does not match the expected patterns.
- Training the system to recognize and authenticate users based on their typical content usage patterns.
Problems solved by this technology:
- Addressing the issue of unauthorized access to mobile devices and sensitive information.
- Providing an additional layer of security by analyzing the content being rendered during a session.
- Reducing the risk of data breaches and unauthorized usage of computing devices.
Benefits of this technology:
- Improved security and protection of sensitive information on mobile devices.
- Enhanced user authentication by considering the content being rendered, rather than relying solely on traditional methods like passwords.
- Ability to adapt and learn from user behavior to improve the accuracy of authentication.
Original Abstract Submitted
Systems and methods are provided for a content-based security for computing devices. An example method includes identifying content rendered by a mobile application, the content being rendered during a session, generating feature vectors from the content and determining that the feature vectors do not match a classification model. The method also includes providing, in response to the determination that the feature vectors do not match the classification model, a challenge configured to authenticate a user of the mobile device. Another example method includes determining a computing device is located at a trusted location, capturing information from a session, the information coming from content rendered by a mobile application during the session, generating feature vectors for the session, and repeating this until a training criteria is met. The method also includes training a classification model using the feature vectors and authenticating a user of the device using the trained classification model.