Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.11126 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910304310394880 |
|---|---|
| author | Zhang, Hangsheng Liu, Jiqiang Dong, Jinsong |
| author_facet | Zhang, Hangsheng Liu, Jiqiang Dong, Jinsong |
| contents | Ensemble defenses, are widely employed in various security-related applications to enhance model performance and robustness. The widespread adoption of these techniques also raises many questions: Are general ensembles defenses guaranteed to be more robust than individuals? Will stronger adaptive attacks defeat existing ensemble defense strategies as the cybersecurity arms race progresses? Can ensemble defenses achieve adversarial robustness to different types of attacks simultaneously and resist the continually adjusted adaptive attacks? Unfortunately, these critical questions remain unresolved as there are no platforms for comprehensive evaluation of ensemble adversarial attacks and defenses in the cybersecurity domain. In this paper, we propose a general Cybersecurity Adversarial Robustness Evaluation (CARE) platform aiming to bridge this gap. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_11126 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CARE: Ensemble Adversarial Robustness Evaluation Against Adaptive Attackers for Security Applications Zhang, Hangsheng Liu, Jiqiang Dong, Jinsong Cryptography and Security Machine Learning Ensemble defenses, are widely employed in various security-related applications to enhance model performance and robustness. The widespread adoption of these techniques also raises many questions: Are general ensembles defenses guaranteed to be more robust than individuals? Will stronger adaptive attacks defeat existing ensemble defense strategies as the cybersecurity arms race progresses? Can ensemble defenses achieve adversarial robustness to different types of attacks simultaneously and resist the continually adjusted adaptive attacks? Unfortunately, these critical questions remain unresolved as there are no platforms for comprehensive evaluation of ensemble adversarial attacks and defenses in the cybersecurity domain. In this paper, we propose a general Cybersecurity Adversarial Robustness Evaluation (CARE) platform aiming to bridge this gap. |
| title | CARE: Ensemble Adversarial Robustness Evaluation Against Adaptive Attackers for Security Applications |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2401.11126 |