Generating Natural Language Adversarial Examples

@inproceedings{Alzantot2018GeneratingNL,
  title={Generating Natural Language Adversarial Examples},
  author={Moustafa Alzantot and Yash Sharma and Ahmed Elgohary and Bo-Jhang Ho and Mani B. Srivastava and Kai-Wei Chang},
  booktitle={EMNLP},
  year={2018}
}
Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify. In the image domain, these perturbations are often virtually indistinguishable to human perception, causing humans and state-of-the-art models to disagree. However, in the natural language domain, small perturbations are clearly perceptible, and the replacement of a single word can drastically alter the semantics of the document. Given… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 53 CITATIONS

Certified Robustness to Adversarial Word Substitutions

VIEW 20 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Natural Language Adversarial Attacks and Defenses in Word Level

Xiaosen Wang, Hao Jin, Kun He
  • ArXiv
  • 2019
VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Soft Representation Learning for Sparse Transfer

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

On the Robustness of Self-Attentive Models

VIEW 3 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

Structure-Invariant Testing for Machine Translation

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2018
2019

CITATION STATISTICS

  • 11 Highly Influenced Citations

  • Averaged 28 Citations per year from 2018 through 2019

  • 360% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 27 REFERENCES

Intriguing properties of neural networks

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL