OpenBackdoor: A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks
Reading notes about OpenBackdoor.
Abstract
This paper focus on textual backdoor attacks, which highlights two issues in privious backdoor learning evaluations:
- real-wolrd scenarios differs
- evaluation ignore that poisoned samples’ stealthy and semantic-preserving
Contribution:
- categorize existing scenarios
- new stealthy and semantic-preserving metrics
All articles in this blog are licensed under CC BY-NC-SA 4.0 unless stating additionally.