Home > Research > Researchers > Mr William Hackett > Publications

William Hackett

Research student

  1. 2023
  2. Published

    Compilation as a Defense: Enhancing DL Model Attack Robustness via Tensor Optimization

    Trawicki, S., Hackett, W., Birch, L., Suri, N. & Garraghan, P., 20/10/2023. 2 p.

    Research output: Contribution to conference - Without ISBN/ISSN Conference paperpeer-review

  3. Published

    Model Leeching: An Extraction Attack Targeting LLMs

    Birch, L., Hackett, W., Trawicki, S., Suri, N. & Garraghan, P., 20/10/2023.

    Research output: Contribution to conference - Without ISBN/ISSN Conference paperpeer-review

  4. 2022
  5. Published

    Pinch: An Adversarial Extraction Attack Framework for Deep Learning Models

    Hackett, W., Trawicki, S., Yu, Z., Suri, N. & Garraghan, P., 13/09/2022, In: arXiv.

    Research output: Contribution to Journal/MagazineJournal article

  6. Published

    PINCH: An Adversarial Extraction Attack Framework for Deep Learning Models.

    Hackett, W., Trawicki, S., Yu, Z., Suri, N. & Garraghan, P., 13/09/2022, In: arXiv. abs/2209.06300, 15 p.

    Research output: Contribution to Journal/MagazineJournal articlepeer-review

Back to top