On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models

NAACL 2019 Paul MichelXian LiGraham NeubigJuan Miguel Pino

Adversarial examples --- perturbations to the input of a model that elicit large changes in the output --- have been shown to be an effective way of assessing the robustness of sequence-to-sequence (seq2seq) models. However, these perturbations only indicate weaknesses in the model if they do not change the input so significantly that it legitimately results in changes in the expected output... (read more)

PDF Abstract NAACL 2019 PDF NAACL 2019 Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper