International Business Machines Corporation

Vinh Tuan Thai

Luke Taher

Dana Lea Price

Ian Manning

Ryan T Claussen

Paul M Barry

Jack Richard Buggins

Paul Barry

Madeleine Frost

An approach for training a recurrent neural network to create a model for anomaly detection in the topology of a network is disclosed. The approach comprises, creating an embedding vector for each resource in the network based on applying an embedding algorithm to each resource of the network. A feature vector is then created for each change to a resource in the network based on one or more properties of the change. A recurrent neural network can thus be trained with the embedding vectors and the feature vectors to create a model for anomaly detection in the topology of the network.

Anomaly detection in network topology

Method and system are provided for user authentication using original and modified images. The method includes receiving an original image for a user, where the original image is a private image that meets certain configured criteria. The method uses a pre-trained Convolutional Neural Network (CNN) model to extract one or more image features of the original image and feeds the extracted image feature into a Generative Adversarial Network (GAN) image generator to realistically modify the extracted image feature to generate a modified image. The method authenticates a user based on recognition of a presented original image or a presented modified image.

User authentication using original and modified images

A method analyzes applications for modernization. Processor units analyze each application in the applications in isolation from other applications to identify issues in code for the applications and a number of common code components. The processor units create a directed graph structure using the issues identified in the applications and the number of common code components. The directed graph structure includes relationships between the applications, the number of common code components, and the issues identified. The processor units determine a common code component modernization cost for the number of common code components using the directed graph structure. The processor units determine an application modernization cost for a set of the applications using the directed graph structure. The application modernization cost for the set of the applications takes into account the common code component cost for modernizing the number of common code components a single time.

Application modernization

Growing community of inventors

Markham, Canada

Vinh Tuan Thai