Abstract: A system and method for preventing erroneous data entry is disclosed. When presented with a form, such as in a website or an app, users are often requested to submit private information that should not be made public. However, form fields are often not protected, and users commonly erroneously enter private information into forms requesting non-private information. Therefore, an alternative entry display is provided to the user to allow the user to separately and securely submit form field entries. This display analyzes the information provided to the user to determine the type of data being requested by a selected form field. This information is used not only to prompt the user in the alternative entry display, but also to verify that the information provided by the user matches the type being requested for security purposes.

Abstract: Methods and systems are described herein for minimizing the computational and/or storage cost of computer resources when analyzing multi-modal data. A system may receive a multi-modal input using one or more sensors. The system inputs the multi-modal input into a first preprocessor to generate a first output of a single modal data format. The system then inputs the first output into an artificial intelligence (AI) model trained to determine classifications of inputted data and confidence measures for each classification. The output from the AI model indicates a first classification and a first confidence measure for the first classification. In response to determining that the first confidence measure does not correspond to a threshold confidence measure, the system selects a second preprocessor having a greater computational cost than the first preprocessor. Then the system may input the multi-modal input into the second preprocessor to generate a second output.

Abstract: Disclosed herein are system, method, and computer program product embodiments for determining a probability of a device at risk. The device may be associated with a plurality of security parameters. For a security parameter, the device can be in multiple states. A probability value corresponding to a security parameter can indicate the security parameter being in a state among the multiple states. A probabilistic graphical model may be used to represent dependences of the plurality of security parameters. A device security risk prediction module may determine a probability of the device at risk based on the probabilistic graphical model and the probability assignments to the plurality of nodes of the probabilistic graphical model, and further determine a user action instruction to be provided to a user of the device based on the probability of the device at risk.

Abstract: Systems and methods are disclosed herein for determining a source of leaked sensitive data (e.g., passwords, insecure coding, log information, any information that should not exist, etc.) in compiled software applications. According to some aspects, a computing device (e.g., a software analysis device, a cloud-computing device, a server, a smart device, binary file/code scanner, etc.) may receive scan pattern information and a binary file of a software application. The computing device may be configured to determine one or more executable files of the software application based on the binary file. Based on the scan pattern information and the one or more executable files, the computing device may determine location information for one or more sensitive data elements configured with the software application. The computing device may use the location information for each of the one or more sensitive data elements to determine a respective source of the sensitive data element.

Abstract: Systems and methods for securing data for outbound communication may include: determining a risk profile for the outbound communication based, the outbound communication comprising data modules including at least a payload, an origination endpoint, and a destination endpoint; determining a scanning policy from a plurality of scanning policies, based on the determined risk profile; determining a secure machine learning model from a plurality of secure machine learning models, based on the determined risk profile, wherein the secure machine learning model is determined based on an authentication level corresponding to the determined risk profile; providing one or more data modules to the secure machine learning model, based on the determined scanning policy; receiving a sanitized version of the payload based on an output of the secure machine learning model; and providing the sanitized version of the payload for the outbound communication.

Abstract: Systems and methods are disclosed herein for determining a source of leaked sensitive data (e.g., passwords, insecure coding, log information, any information that should not exist, etc.) in compiled software applications. According to some aspects, a computing device (e.g., a software analysis device, a cloud-computing device, a server, a smart device, binary file/code scanner, etc.) may receive scan pattern information and a binary file of a software application. The computing device may be configured to determine one or more executable files of the software application based on the binary file. Based on the scan pattern information and the one or more executable files, the computing device may determine location information for one or more sensitive data elements configured with the software application. The computing device may use the location information for each of the one or more sensitive data elements to determine a respective source of the sensitive data element.

Abstract: A ball returning backstop assembly includes a backstop that collects a thrown ball and a ball return assembly that returns the collected ball. The ball return assembly includes a housing that supports a linkage for propelling the collected ball and a motor for driving the linkage. The housing includes a tube that receives the collected ball, with the linkage having a piston that is slidable within the tube to propel the ball out of the tube. The motor is electrically connected to switches that control when the motor drives the linkage. One switch being configured to turn the motor on when the collected ball is ready to be returned and the other switch being configured to turn the motor off after the ball is propelled out of the tube.