恶意软件 C&C 流量深度学习检测器规避 (AML.CS0000)

一句话通俗理解

Palo Alto 安全 AI 研究团队用公开数据集逆向了一个恶意 C&C 流量检测模型，发现无需恶意样本也能构造出绕过检测的流量。

维度	内容
案例类型	演练 / 安全研究
发生时间	2020-01-01
攻击者	Palo Alto Networks AI Research Team
受害目标	Palo Alto Networks malware detection system

Palo Alto Networks 安全 AI 研究团队对 HTTP 流量中的恶意软件命令与控制（C&C）检测深度学习模型进行了红队测试。基于公开可得的训练数据，团队构建了替代模型，据此构造出规避样本——证明攻击者无需接触原模型即可实现检测规避。

以下攻击链映射来自 MITRE ATLAS 官方数据（AML.CS0000 的 employs 关系），按官方步骤编号排序；技术名称链接至本库对应技术文档，引用文字为官方对本次运用的描述。

预印本仓库 (AML.T0000.001)

We identified a machine learning based approach to malicious URL detection as a representative approach and potential target from the paper URLNet: Learning a URL representation with deep learning for malicious URL detection, which was found on arXiv (a pre-print repository).

数据集 (AML.T0002.000)

We acquired a command and control HTTP traffic dataset consisting of approximately 33 million benign and 27 million malicious HTTP packet headers.

创建代理 AI 模型 (AML.T0005)

We trained a model on the HTTP traffic dataset to use as a proxy for the target model. Evaluation showed a true positive rate of ~ 99% and false positive rate of ~ 0.01%, on average. Testing the model with a HTTP packet header from known malware command and control traffic samples was detected as malicious with high confidence (> 99%).

人工修改 (AML.T0043.003)

We crafted evasion samples by removing fields from packet header which are typically not used for C&C communication (e.g. cache-control, connection, etc.).

验证攻击 (AML.T0042)

We queried the model with our adversarial examples and adjusted them until the model was evaded.

规避 AI 模型 (AML.T0015)

With the crafted samples, we performed online evasion of the ML-based spyware detection model. The crafted packets were identified as benign with > 80% confidence. This evaluation demonstrates that adversaries are able to bypass advanced ML detection techniques, by crafting samples that are misclassified by an ML model.

以下为 MITRE ATLAS 官方案例收录的参考来源：

版本: ATLAS 2026.09 | 更新: 2026-10-24 | 模板: ATLAS 案例研究 v1.0