将规则检测融入AI训练，提升病毒识别抗干扰能力
Demystifying the Role of Rule-based Detection in AI Systems for Windows Malware Detection
- 用未被规则标记的样本训练模型，降低数据复杂度
- 对抗样本和时间漂移下检测准确率提升，但误报有下限
- 适合关注安全系统鲁棒性的研究人员参考
恶意软件检测越来越多地依赖结合签名检测与机器学习的AI系统。然而，这些组件通常独立开发和集成，错失了降低数据复杂性和增强对对抗性样本（精心设计以规避检测的程序）防御力的机会。本文研究了在训练流程中引入签名检测的影响。我们对比了在全量数据上训练的模型，与仅使用未被签名标记的样本训练的AI系统。结果表明，后者在面对对抗样本和时间数据漂移时表现出更强的鲁棒性，但代价是存在由规则选择不佳导致的固定最低误报率。最后，我们讨论了这些局限性，并提出未来研究可引入动态分析以进一步提升系统韧性。
原文摘要 · Abstract (English)
Malware detection increasingly relies on AI systems that integrate signature-based detection with machine learning. However, these components are typically developed and combined in isolation, missing opportunities to reduce data complexity and strengthen defenses against adversarial EXEmples, carefully crafted programs designed to evade detection. Hence, in this work we investigate the influence that signature-based detection exerts on model training, when they are included inside the training pipeline. Specifically, we compare models trained on a comprehensive dataset with an AI system whose machine learning component is trained solely on samples not already flagged by signatures. Our results demonstrate improved robustness to both adversarial EXEmples and temporal data drift, although this comes at the cost of a fixed lower bound on false positives, driven by suboptimal rule selection. We conclude by discussing these limitations and outlining how future research could extend AI-based malware detection to include dynamic analysis, thereby further enhancing system resilience.
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。