Microsoft Technology Licensing, LLC

Amazon Technologies, Inc.

Feng Xue

Jesper Mikael Johansson

Bin Benjamin Zhu

Gang Liu

Cheng Hung Hui

Weibo Chu

Techniques are described for using a credential, such as a user identifier associated with an account on a first service, to create a reusable account on a second service. The account may be initially activated based on the receipt of a passcode sent to the account on the first service. The account may be created with access to a subset of features on the second service. On receiving a password for the account, the account may be modified to access a broader feature set. The account may be reusable via a cookie or other token placed on a user device, and reusability may be disabled on detecting possible security risk conditions associated with the user identifier.

Account generation based on external credentials

The techniques described herein use training data to train classification models to detect malicious Uniform Resource Locators (URLs) that target authentic resources (e.g., Web page, Web site, or other network locations accessed via a URL). The techniques train the classification models using one or more machine learning algorithms. The training data may include known benign URLs and known malicious URLs (e.g., training URLs) that are associated with a target authentic resource. The techniques then use the trained classification models to determine whether an unknown URL is a malicious URL. The malicious URL determination may be based on one or more lexical features (e.g., brand name edit distances for a domain and path of the URL) and/or site/page features (e.g., a domain age and a domain confidence level) extracted.

Malicious uniform resource locator detection

Growing community of inventors

Beijing, China

Feng Xue