ML Anthology

Towards Adversarially Robust Knowledge Graph Embeddings

Peru Bhardwaj
AAAI 2020 pp. 13712-13713
doi:10.1609/AAAI.V34I10.7128 /aaai/2020/bhardwaj2020aaai-adversarially/

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.

PDF AAAI Semantic Scholar

Cite

Text

Bhardwaj. "Towards Adversarially Robust Knowledge Graph Embeddings." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I10.7128

Markdown

[Bhardwaj. "Towards Adversarially Robust Knowledge Graph Embeddings." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/bhardwaj2020aaai-adversarially/) doi:10.1609/AAAI.V34I10.7128

BibTeX

@inproceedings{bhardwaj2020aaai-adversarially,
  title     = {{Towards Adversarially Robust Knowledge Graph Embeddings}},
  author    = {Bhardwaj, Peru},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13712-13713},
  doi       = {10.1609/AAAI.V34I10.7128},
  url       = {https://mlanthology.org/aaai/2020/bhardwaj2020aaai-adversarially/}
}