Certified Robustness
metric
ID: certifiedrobustness
Related Papers
SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions
AbstractState-of-the-art NLP models can often be fooled by human-unaware transformations such as synonymous word substitution. For security reasons, it is of critical importance to develop models with certified robustness that …...
Certified Robustness to Word Substitution Attack with Differential Privacy
AbstractThe robustness and security of natural language processing (NLP) models are significantly important in real-world applications. In the context of text classification tasks, adversarial examples can be designed by substituting …...