Corpus ID: 220249771

Natural Backdoor Attack on Text Data

@article{Sun2020NaturalBA,
  title={Natural Backdoor Attack on Text Data},
  author={Lichao Sun},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.16176}
}
  • Lichao Sun
  • Published 2020
  • Computer Science
  • ArXiv
  • Deep learning has been widely adopted in natural language processing applications in recent years. Many existing studies show the vulnerabilities of machine learning and deep learning models against adversarial examples. However, most existing works currently focus on evasion attack on text data instead of positioning attack, also named backdoor attack. In this paper, we systematically study the backdoor attack against models on text data. First, we define the backdoor attack on text data. Then… CONTINUE READING

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 22 REFERENCES

    Defending against Backdoor Attack on Deep Neural Networks

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Language Models are Few-Shot Learners

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Deep Residual Learning for Image Recognition

    VIEW 1 EXCERPT