arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.14906cs.CR
收藏

针对基于机器学习的恶意流量检测系统的硬标签黑盒逃逸攻击

A Hard-Label Black-Box Evasion Attack against ML-based Malicious Traffic Detection Systems

Tsinghua University(清华大学);Beijing Institute of Technology(北京理工大学);Zhongguancun Lab(中关村实验室)

Zixuan Liu, Yi Zhao, Zhuotao Liu, Qi Li, Chuanpu Fu, Guangmeng Zhou, Ke Xu

AI总结:

针对基于机器学习的恶意流量检测系统,提出利用强化学习与预训练模型Traffic-BERT的硬标签黑盒逃逸攻击NetMasquerade,在80种场景下对6种检测方法实现超96.65%成功率。

摘要:

基于机器学习(ML)的恶意流量检测是一种前景广阔的安全范式。它通过识别各种高级攻击,优于基于规则的传统检测方法。然而,这些机器学习模型的鲁棒性在很大程度上尚未被探索,从而使攻击者能够构造逃逸检测的对抗性流量样本。现有的逃逸攻击通常依赖于过度限制的条件(例如,加密协议、Tor或专门设置),或需要关于目标的详细先验知识(例如,训练数据和模型参数),这在现实的黑盒场景中是不切实际的。因此,硬标签黑盒逃逸攻击(即在无需目标内部信息的情况下适用于多种任务和协议)的可行性仍然是一个开放的挑战。为此,我们开发了NetMasquerade,它利用强化学习(RL)来操纵攻击流量以模仿良性流量并逃逸检测。具体而言,我们建立了一个定制的预训练模型Traffic-BERT,利用网络专用的分词器和注意力机制来提取多样的良性流量模式。随后,我们将Traffic-BERT集成到强化学习框架中,使NetMasquerade能够基于良性流量模式以最小的修改有效操纵恶意数据包序列。实验结果表明,NetMasquerade使暴力攻击和隐蔽攻击都能在80种攻击场景下逃逸6种现有检测方法,实现了超过96.65%的攻击成功率。值得注意的是,它可以逃逸那些在经验上或可证明地对现有逃逸攻击具有鲁棒性的方法。最后,NetMasquerade实现了低延迟的对抗性流量生成,展示了其在现实场景中的实用性。

英文摘要:

Machine Learning (ML)-based malicious traffic detection is a promising security paradigm. It outperforms rule-based traditional detection by identifying various advanced attacks. However, the robustness of these ML models is largely unexplored, thereby allowing attackers to craft adversarial traffic examples that evade detection. Existing evasion attacks typically rely on overly restrictive conditions (e.g., encrypted protocols, Tor, or specialized setups), or require detailed prior knowledge of the target (e.g., training data and model parameters), which is impractical in realistic black-box scenarios. The feasibility of a hard-label black-box evasion attack (i.e., applicable across diverse tasks and protocols without internal target insights) thus remains an open challenge. To this end, we develop NetMasquerade, which leverages reinforcement learning (RL) to manipulate attack flows to mimic benign traffic and evade detection. Specifically, we establish a tailored pre-trained model called Traffic-BERT, utilizing a network-specialized tokenizer and an attention mechanism to extract diverse benign traffic patterns. Subsequently, we integrate Traffic-BERT into the RL framework, allowing NetMasquerade to effectively manipulate malicious packet sequences based on benign traffic patterns with minimal modifications. Experimental results demonstrate that NetMasquerade enables both brute-force and stealthy attacks to evade 6 existing detection methods under 80 attack scenarios, achieving over 96.65% attack success rate. Notably, it can evade the methods that are either empirically or certifiably robust against existing evasion attacks. Finally, NetMasquerade achieves low-latency adversarial traffic generation, demonstrating its practicality in real-world scenarios.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑