Paypal, Inc.

Faisal M Khan

Abraham J Kang

Bharat Chandra Penta

Vinh Nguyen

Casey Ian Abernathy

Ilya Volodin

Antonio Montanez, Jr

Kevin Charles Griffin

Techniques are disclosed relating to methods that include training, by a new profile process executing on a computer system, a contrastive loss function to identify fraudulent images associated with a particular entity. The new profile process may receive new profile information that includes a new profile image and a new profile identifier and compare the new profile identifier to one or more existing profile identifiers. In response to determining that one or more existing profile identifiers satisfy a threshold identifier metric, a particular neural network, using the contrastive loss function, may compare the new profile image to one or more existing profile images corresponding to the one or more existing profile identifiers. The new profile process may determine, using the comparing, whether the new profile information is a possible fake profile of a legitimate profile.

Identification of fraudulent online profiles

Systems and/or techniques for facilitating automatic detection of proxy-based phishing sites are provided. In various embodiments, a system can access a computer-executable web resource and can embed an authorization verification logic within the computer-executable web resource. In various aspects, upon execution of the computer-executable web resource, the authorization verification logic can be configured to: identify a computing domain via which the computer-executable web resource is being executed; compare the identified computing domain with one or more authorized computing domains; determine that the identified computing domain is an unauthorized proxy site if the identified computing domain does not match at least one of the one or more authorized computing domains; and initiate a remedial action based on determining that the identified computing domain is an unauthorized proxy site.

Automatic detection of proxy-based phishing sites

Systems and/or techniques for facilitating relay attack prevention for electronic quick response (QR) codes are provided. In various embodiments, a system can determine a cardinality and a frame rate. In various aspects, the system can transmit a first electronic instruction to a mobile device, which can cause the mobile device to generate a set of interlaced frames having the determined cardinality. In various cases, the set of interlaced frames can respectively correspond to a set of portions of an electronic QR code, such that different frames from the set of interlaced frames depict different portions from the set of portions of the electronic QR code. In various aspects, the first electronic instruction can further cause the mobile device to sequentially render, at the determined frame rate, the set of interlaced frames on an electronic display of the mobile device. In various aspects, this can cause one portion from the set of portions of the electronic QR code to be depicted on the electronic display at a time. In various instances, the system can transmit a second electronic instruction to a point-of-sale device, which can cause the point-of-sale device to reconfigure scanner settings of the point-of-sale device, and which can enable the point-of-sale device to capture the set of interlaced frames sequentially rendered on the electronic display of the mobile device based on the determined cardinality and the determined frame rate.

Relay attack prevention for electronic QR codes

Growing community of inventors

Berkeley, CA, United States of America

Faisal M Khan