Robust Encodings: A Framework for Combating Adversarial Typos

ACL 2020 Erik JonesRobin JiaAditi RaghunathanPercy Liang

Despite excellent performance on many tasks, NLP systems are easily fooled by small adversarial perturbations of inputs. Existing procedures to defend against such perturbations are either (i) heuristic in nature and susceptible to stronger attacks or (ii) provide guaranteed robustness to worst-case attacks, but are incompatible with state-of-the-art models like BERT... (read more)

PDF Abstract ACL 2020 PDF ACL 2020 Abstract

Code


No code implementations yet. Submit your code now

Tasks


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