Search Results for author:
Found 5 papers, 0 papers with code
Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks
The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks.
Certifiable Black-Box Attack: Ensuring Provably Successful Attack for Adversarial Examples
To craft the adversarial examples with the certifiable attack success rate (CASR) guarantee, we design several novel techniques, including a randomized query method to query the target model, an initialization method with smoothed self-supervised perturbation to derive certifiable adversarial examples, and a geometric shifting method to reduce the perturbation size of the certifiable adversarial examples for better imperceptibility.
Certified Adversarial Robustness via Anisotropic Randomized Smoothing
However, all of the existing methods rely on fixed i. i. d.
UniCR: Universally Approximated Certified Robustness via Randomized Smoothing
We study certified robustness of machine learning classifiers against adversarial perturbations.
An Eye for an Eye: Defending against Gradient-based Attacks with Gradients
In this paper, we show that the gradients can also be exploited as a powerful weapon to defend against adversarial attacks.
