This paper proposes a fast and scalable method for uncertainty quantific...
Randomized smoothing is considered to be the state-of-the-art provable
d...
Supporting the current trend in the AI community, we propose the AI Jour...
In safety-critical machine learning applications, it is crucial to defen...
Manifold hypothesis states that data points in high-dimensional space
ac...
We propose a novel approach of randomized smoothing over multiplicative
...
Several methods for inversion of face recognition models were recently
p...
We present a new state-of-the-art on the text to video retrieval task on...
The knowledge that data lies close to a particular submanifold of the am...
Differential privacy is a powerful and gold-standard concept of measurin...
The construction of models for video action classification progresses
ra...
In this work, we present a novel algorithm based on an it-erative sampli...
State-of-the-art deep learning models are untrustworthy due to their
vul...
Recent works showed the vulnerability of image classifiers to adversaria...
Recent studies proved that deep learning approaches achieve remarkable
r...
In this paper we propose a novel easily reproducible technique to attack...