GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models
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_ | 1866917003993808896 |
|---|---|
| author | Luo, Haozheng Qiu, Chenghao Wang, Yimin Wu, Shang Yu, Jiahao Pan, Zhenyu Mao, Weian Fang, Haoyang Xu, Hao Liu, Han Wang, Binghui Chen, Yan |
| author_facet | Luo, Haozheng Qiu, Chenghao Wang, Yimin Wu, Shang Yu, Jiahao Pan, Zhenyu Mao, Weian Fang, Haoyang Xu, Hao Liu, Han Wang, Binghui Chen, Yan |
| contents | We propose the first unified adversarial attack benchmark for Genomic Foundation Models (GFMs), named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first comprehensive evaluation framework to systematically assess the vulnerability of GFMs to adversarial attacks. Methodologically, we evaluate the adversarial robustness of five state-of-the-art GFMs using four widely adopted attack algorithms and three defense strategies. Importantly, our benchmark provides an accessible and comprehensive framework to analyze GFM vulnerabilities with respect to model architecture, quantization schemes, and training datasets. Additionally, we introduce GenoAdv, a new adversarial sample dataset designed to improve GFM safety. Empirically, classification models exhibit greater robustness to adversarial perturbations compared to generative models, highlighting the impact of task type on model vulnerability. Moreover, adversarial attacks frequently target biologically significant genomic regions, suggesting that these models effectively capture meaningful sequence features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_10983 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models Luo, Haozheng Qiu, Chenghao Wang, Yimin Wu, Shang Yu, Jiahao Pan, Zhenyu Mao, Weian Fang, Haoyang Xu, Hao Liu, Han Wang, Binghui Chen, Yan Machine Learning Artificial Intelligence Cryptography and Security We propose the first unified adversarial attack benchmark for Genomic Foundation Models (GFMs), named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first comprehensive evaluation framework to systematically assess the vulnerability of GFMs to adversarial attacks. Methodologically, we evaluate the adversarial robustness of five state-of-the-art GFMs using four widely adopted attack algorithms and three defense strategies. Importantly, our benchmark provides an accessible and comprehensive framework to analyze GFM vulnerabilities with respect to model architecture, quantization schemes, and training datasets. Additionally, we introduce GenoAdv, a new adversarial sample dataset designed to improve GFM safety. Empirically, classification models exhibit greater robustness to adversarial perturbations compared to generative models, highlighting the impact of task type on model vulnerability. Moreover, adversarial attacks frequently target biologically significant genomic regions, suggesting that these models effectively capture meaningful sequence features. |
| title | GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models |
| topic | Machine Learning Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2505.10983 |