An Empirical Study of Aegis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929326267564032 |
|---|---|
| author | Saragih, Daniel Goel, Paridhi Balaji, Tejas Li, Alyssa |
| author_facet | Saragih, Daniel Goel, Paridhi Balaji, Tejas Li, Alyssa |
| contents | Bit flipping attacks are one class of attacks on neural networks with numerous defense mechanisms invented to mitigate its potency. Due to the importance of ensuring the robustness of these defense mechanisms, we perform an empirical study on the Aegis framework. We evaluate the baseline mechanisms of Aegis on low-entropy data (MNIST), and we evaluate a pre-trained model with the mechanisms fine-tuned on MNIST. We also compare the use of data augmentation to the robustness training of Aegis, and how Aegis performs under other adversarial attacks, such as the generation of adversarial examples. We find that both the dynamic-exit strategy and robustness training of Aegis has some drawbacks. In particular, we see drops in accuracy when testing on perturbed data, and on adversarial examples, as compared to baselines. Moreover, we found that the dynamic exit-strategy loses its uniformity when tested on simpler datasets. The code for this project is available on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15784 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Empirical Study of Aegis Saragih, Daniel Goel, Paridhi Balaji, Tejas Li, Alyssa Machine Learning Bit flipping attacks are one class of attacks on neural networks with numerous defense mechanisms invented to mitigate its potency. Due to the importance of ensuring the robustness of these defense mechanisms, we perform an empirical study on the Aegis framework. We evaluate the baseline mechanisms of Aegis on low-entropy data (MNIST), and we evaluate a pre-trained model with the mechanisms fine-tuned on MNIST. We also compare the use of data augmentation to the robustness training of Aegis, and how Aegis performs under other adversarial attacks, such as the generation of adversarial examples. We find that both the dynamic-exit strategy and robustness training of Aegis has some drawbacks. In particular, we see drops in accuracy when testing on perturbed data, and on adversarial examples, as compared to baselines. Moreover, we found that the dynamic exit-strategy loses its uniformity when tested on simpler datasets. The code for this project is available on GitHub. |
| title | An Empirical Study of Aegis |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.15784 |