research
∙
07/31/2023
Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks
The language models, especially the basic text classification models, ha...
share
research
∙
04/10/2023
Certifiable Black-Box Attack: Ensuring Provably Successful Attack for Adversarial Examples
Black-box adversarial attacks have shown strong potential to subvert mac...
research
∙
09/29/2022
L-SRR: Local Differential Privacy for Location-Based Services with Staircase Randomized Response
Location-based services (LBS) have been significantly developed and wide...
research
∙
07/12/2022
Certified Adversarial Robustness via Anisotropic Randomized Smoothing
Randomized smoothing has achieved great success for certified robustness...
research
∙
07/05/2022
UniCR: Universally Approximated Certified Robustness via Randomized Smoothing
We study certified robustness of machine learning classifiers against ad...
research
∙
02/02/2022