Large language models (LLMs) released for public use incorporate guardra...
The literature on provable robustness in machine learning has primarily
...
Certified robustness in machine learning has primarily focused on advers...
The study of provable adversarial robustness for deep neural network (DN...
Randomized smoothing has been successfully applied in high-dimensional i...
Randomized smoothing is a popular way of providing robustness guarantees...
Randomized smoothing has been shown to provide good certified-robustness...
Despite the vulnerability of object detectors to adversarial attacks, ve...
Randomized smoothing, using just a simple isotropic Gaussian distributio...
Clustering is a fundamental tool in data mining. It partitions points in...