A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
BadNL: Backdoor Attacks Against NLP Models
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
In this paper, we present the first systematic investigation of the backdoor attack against models designed for natural language processing (NLP) tasks. ...
For instance, using the word-level triggers, our backdoor attack achieves 100% backdoor accuracy with only a drop of 0.18%, 1.26%, and 0.19% in the models utility, for the IMDB, Amazon, and Stanford Sentiment ...
Conclusion In this work, we explore the backdoor attacks against NLP models. ...
arXiv:2006.01043v1
fatcat:a627azfbfzam5ck4sx6gfyye34