Siemens Aktiengesellschaft

Ayse Parlak

Suraj Ravi Musuvathy

Leandro Pfleger De Aguiar

Lucia Mirabella

Erhan Arisoy

Enrico Lovat

Tobias Mainka

System and method are disclosed for preserving privacy of shared data over a shared network. A vector encoder transforms received data into a feature vector. An autoencoder includes a neural network-based encoder transforms the feature vector into a fixed size latent space representation of the received data. A neural network-based decoder of the autoencoder is configured to reconstruct the feature vector from the latent space representation. The autoencoder is trained using training data with an objective to minimize reconstruction error. A vector decoder transforms the reconstructed feature vector into reconstructed data. The latent space representation of data from the trained autoencoder is shared as anonymized data with at least one trusted party over the shared network, decoded offline using a replica of the trained decoder.

Privacy preservation of data over a shared network

A system and a method for automatically clustering sandbox analysis reports of similar malware samples. An automated malware analysis process includes receiving from a sandbox server the sandbox analysis reports of the similar malware samples at an application programming interface (API) of the clustering server, clustering similar Uniform Resource Locators (URLs) together and clustering the sandbox analysis reports of events in sandbox reports clusters (-) based on the URL clustering, static properties of the malware samples and dynamic properties of the malware samples.

Automated malware analysis that automatically clusters sandbox reports of similar malware samples

A computer-implemented method of optimized lattice partitioning of solid 3-D models for additive manufacturing includes a computer receiving a 3-D model of an object to be printed and functional specifications indicating desired mechanical properties for portions of the object. The computer generates a plurality of lattice template structures based on the 3-D model and a uniform grid structure of an internal surface of the object. The computer determines material behaviors for each of the plurality of lattice template structures using the functional specifications and assigns the lattice template structures to locations in the uniform grid structure based on the material behaviors of the lattice template structures, thereby yielding a printable lattice.

Growing community of inventors

Princeton, NJ, United States of America

Ayse Parlak