首个基因组大模型抗攻击评估框架，揭示模型脆弱性与生物功能区域关联
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models
- 构建统一评测框架GenoArmory，系统测试五种主流基因组大模型的抗攻击能力
- 生成模型比分类模型更易受攻击，且攻击多集中于重要生物基因区段
- 提供新对抗样本数据集GenoAdv，助力提升基因组模型安全性
我们提出首个针对基因组基础模型（GFMs）的统一对抗攻击基准——GenoArmory。与现有基准不同，GenoArmory首次提供系统化评估框架，全面分析GFMs在对抗攻击下的脆弱性。方法上，采用四种主流攻击算法和三种防御策略，评估五种前沿GFMs的鲁棒性。该框架还支持分析模型架构、量化方案及训练数据集对脆弱性的影响。此外，我们构建了新对抗样本数据集GenoAdv，以增强基因组模型的安全性。实验表明，分类模型对抗扰动的鲁棒性高于生成模型，且攻击常集中于具有生物学意义的基因组区域，说明模型有效捕捉了关键序列特征。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。