University of California

Siemens Aktiengesellschaft

Jiang Wan

Mohammad Abdullah Al Faruque

Sujit Rokka Chhetri

Arquimedes Martinez Canedo

Anthony Bahadir Lopez

Sina Faezi

Blake Pollard

A computer-implemented method for learning structural relationships between nodes of a graph includes generating a knowledge graph comprising nodes representing a system and applying a graph-based convolutional neural network (GCNN) to the knowledge graph to generate feature vectors describing structural relationships between the nodes. The GCNN comprises: (i) a graph feature compression layer configured to learn subgraphs representing embeddings of the nodes of the knowledge graph into a vector space, (ii) a neighbor nodes aggregation layer configured to derive neighbor node feature vectors for each subgraph and aggregate the neighbor node feature vectors with their corresponding subgraphs to yield aggregated subgraphs, and (iii) a subgraph convolution layer configured to generate the feature vectors based on the aggregated subgraphs. Functional groups of components included in the system may then be identified based on the plurality of feature vectors.

SGCNN: structural graph convolutional neural network

A methodology as described herein allows cyber-domain tools such as computer aided-manufacturing (CAM) to be aware of the existing information leakage. Then, either machine process or product design parameters in the cyber-domain are changed to minimize the information leakage. This methodology aids the existing cyber-domain and physical-domain security solution by utilizing the cross-domain relationship.

Information leakage-aware computer aided cyber-physical manufacturing

A novel methodology for providing security to maintain the confidentiality of additive manufacturing systems during the cyber-physical manufacturing process is featured. This solution is incorporated within the computer aided manufacturing tools such as slicing algorithms and the tool-path generation, which are in the cyber-domain. This effectively mitigates the cross domain physical-to-cyber domain attacks which can breach the confidentiality of the manufacturing system to leak valuable intellectual properties.

Defending side channel attacks in additive manufacturing systems

A key generation technique exploiting the randomness of a wireless channel to generate secret keys to secure automotive wireless communication using symmetric cryptography is presented. Moreover, the algorithm of the present technique solves the challenging key exchange problem in automotive wireless communication with low costs in terms of performance and code size. As demonstrated, the proposed algorithm can generate secret keys with 67% average min-entropy. Furthermore, the proposed technique can achieve up to 10&#xd7; performance and 20&#xd7; code size reduction in comparison to the state-of-the-art hybrid cryptographic algorithms.

Growing community of inventors

Irvine, CA, United States of America

Jiang Wan