Abstract | ||
---|---|---|
With the great success of neural networks, it is important to improve the information security of application systems based on them. This paper investigates a scenario where an attacker eavesdrops the intermediate representation computed by the encoder layers and tries to recover the private information of the input text. We propose a new metric to evaluate the encoder's ability to protect privacy and evaluate the Transformer-based encoder, which is the first privacy research conducted on Transformer-based neural networks. We also propose an adversarial training method to enhance the privacy of Transformer-based neural networks. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ISI.2019.8823346 | 2019 IEEE International Conference on Intelligence and Security Informatics (ISI) |
Keywords | Field | DocType |
Privacy protection,Neural network,Transformer,Representation learning | Data mining,Computer science,Transformer,Information security,Encoder,Intermediate language,Artificial neural network,Private information retrieval,Feature learning,Adversarial system | Conference |
ISBN | Citations | PageRank |
978-1-7281-2505-3 | 0 | 0.34 |
References | Authors | |
1 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiaqi Lang | 1 | 0 | 0.34 |
Linjing Li | 2 | 39 | 12.91 |
Weiyun Chen | 3 | 0 | 1.35 |
Daniel Zeng | 4 | 2539 | 286.59 |