Search Results for author:
Found 2 papers, 0 papers with code
Machine Translation Models Stand Strong in the Face of Adversarial Attacks
Through our investigation, we provide evidence that machine translation models display robustness displayed robustness against best performed known adversarial attacks, as the degree of perturbation in the output is directly proportional to the perturbation in the input.
Uncertainty Estimation of Transformers' Predictions via Topological Analysis of the Attention Matrices
In this paper, we propose a method for uncertainty estimation based on the topological properties of the attention mechanism and compare it with classical methods.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
