Killing it with Zero-Shot: Adversarially Robust Novelty Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909466440499200 |
|---|---|
| author | Mirzaei, Hossein Jafari, Mohammad Dehbashi, Hamid Reza Taghavi, Zeinab Sadat Sabokrou, Mohammad Rohban, Mohammad Hossein |
| author_facet | Mirzaei, Hossein Jafari, Mohammad Dehbashi, Hamid Reza Taghavi, Zeinab Sadat Sabokrou, Mohammad Rohban, Mohammad Hossein |
| contents | Novelty Detection (ND) plays a crucial role in machine learning by identifying new or unseen data during model inference. This capability is especially important for the safe and reliable operation of automated systems. Despite advances in this field, existing techniques often fail to maintain their performance when subject to adversarial attacks. Our research addresses this gap by marrying the merits of nearest-neighbor algorithms with robust features obtained from models pretrained on ImageNet. We focus on enhancing the robustness and performance of ND algorithms. Experimental results demonstrate that our approach significantly outperforms current state-of-the-art methods across various benchmarks, particularly under adversarial conditions. By incorporating robust pretrained features into the k-NN algorithm, we establish a new standard for performance and robustness in the field of robust ND. This work opens up new avenues for research aimed at fortifying machine learning systems against adversarial vulnerabilities. Our implementation is publicly available at https://github.com/rohban-lab/ZARND. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_15271 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Killing it with Zero-Shot: Adversarially Robust Novelty Detection Mirzaei, Hossein Jafari, Mohammad Dehbashi, Hamid Reza Taghavi, Zeinab Sadat Sabokrou, Mohammad Rohban, Mohammad Hossein Machine Learning Novelty Detection (ND) plays a crucial role in machine learning by identifying new or unseen data during model inference. This capability is especially important for the safe and reliable operation of automated systems. Despite advances in this field, existing techniques often fail to maintain their performance when subject to adversarial attacks. Our research addresses this gap by marrying the merits of nearest-neighbor algorithms with robust features obtained from models pretrained on ImageNet. We focus on enhancing the robustness and performance of ND algorithms. Experimental results demonstrate that our approach significantly outperforms current state-of-the-art methods across various benchmarks, particularly under adversarial conditions. By incorporating robust pretrained features into the k-NN algorithm, we establish a new standard for performance and robustness in the field of robust ND. This work opens up new avenues for research aimed at fortifying machine learning systems against adversarial vulnerabilities. Our implementation is publicly available at https://github.com/rohban-lab/ZARND. |
| title | Killing it with Zero-Shot: Adversarially Robust Novelty Detection |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.15271 |