Adversarial robustness for machine learning / Pin-Yu Chen and Cho-Jui Hsieh.
Material type:
TextPublisher: London, United Kingdom ; San Diego, California : Academic Press, an imprint of Elsevier, 2023Description: xiv, 283 pages : illustrations ; 23 cmContent type: - text
- still image
- unmediated
- volume
- 9780128240205
- 006.31 C420a 23
- Q325.5 .C44 2023
| Item type | Current library | Shelving location | Call number | Copy number | Status | Date due | Barcode | |
|---|---|---|---|---|---|---|---|---|
Books
|
Main Library | Graduate School Library | GRD 006.31 C420a 2023 (Browse shelf(Opens below)) | 1-2 | Available | 030257 | ||
Books
|
Main Library | Graduate School Library | GRD 006.31 C420a 2023 (Browse shelf(Opens below)) | 2-2 | Available | 030258 |
Includes bibliographical references and index.
Part 1. Preliminaries -- Background and motivation -- Part 2. Adversarial attack -- White-box adversarial attacks -- Black-box adversarial attacks -- Physical adversarial attacks -- Training-time adversarial attacks -- Adversarial attacks beyond image classification -- Part 3. Robustness verification -- Overview of neural network verification -- Incomplete neural network verification -- Complete neural network verification -- Verification against semantic perturbations -- Part 4. Adversarial defense -- Overview of adversarial defense -- Adversarial training -- Randomization-based defense -- Certified robustness training -- Adversary detection -- Adversarial robustness of beyond neural network models -- Adversarial robustness in meta-learning and contrastive learning -- Part 5. Applications beyond attack and defense -- Model reprogramming -- Contrastive explanations -- Model watermarking and fingerprinting -- Data augmentation for unsupervised machine learning.
There are no comments on this title.