Tamp-X: Attacking explainable natural language classifiers through tampered activations

Hassan Ali, Muhammad Suleman Khan, Ala I. Al-Fuqaha, Junaid Qadir 0001. Tamp-X: Attacking explainable natural language classifiers through tampered activations. Computers & Security, 120:102791, 2022. [doi]

@article{AliKAQ22,
  title = {Tamp-X: Attacking explainable natural language classifiers through tampered activations},
  author = {Hassan Ali and Muhammad Suleman Khan and Ala I. Al-Fuqaha and Junaid Qadir 0001},
  year = {2022},
  doi = {10.1016/j.cose.2022.102791},
  url = {https://doi.org/10.1016/j.cose.2022.102791},
  researchr = {https://researchr.org/publication/AliKAQ22},
  cites = {0},
  citedby = {0},
  journal = {Computers & Security},
  volume = {120},
  pages = {102791},
}