Towards Adversarially Robust Knowledge Graph Embeddings

Authors

  • Peru Bhardwaj Trinity College Dublin

DOI:

https://doi.org/10.1609/aaai.v34i10.7128

Abstract

Knowledge graph embedding models enable representation learning on multi-relational graphs and are used in security sensitive domains. But, their security analysis has received little attention. I will research security of these models by designing adversarial attacks against them, improving their adversarial robustness and evaluating the effect of proposed improvement on their interpretability.

Downloads

Published

2020-04-03

How to Cite

Bhardwaj, P. (2020). Towards Adversarially Robust Knowledge Graph Embeddings. Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13712-13713. https://doi.org/10.1609/aaai.v34i10.7128

Issue

Section

Doctoral Consortium Track