Corpus ID: 216641956

Reevaluating Adversarial Examples in Natural Language

@article{Morris2020ReevaluatingAE,
  title={Reevaluating Adversarial Examples in Natural Language},
  author={John X. Morris and Eli Lifland and Jack Lanchantin and Yangfeng Ji and Yanjun Qi},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.14174}
}
  • John X. Morris, Eli Lifland, +2 authors Yanjun Qi
  • Published 2020
  • Computer Science
  • ArXiv
  • State-of-the-art attacks on NLP models have different definitions of what constitutes a successful attack. These differences make the attacks difficult to compare. We propose to standardize definitions of natural language adversarial examples based on a set of linguistic constraints: semantics, grammaticality, edit distance, and non-suspicion. We categorize previous attacks based on these constraints. For each constraint, we suggest options for human and automatic evaluation methods. We use… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 44 REFERENCES

    Generating Natural Language Adversarial Examples

    VIEW 20 EXCERPTS
    HIGHLY INFLUENTIAL