Zixuan Liu (Tsinghua University), Yi Zhao (Beijing Institute of Technology), Zhuotao Liu (Tsinghua University and Zhongguancun Lab), Qi Li (Tsinghua University and Zhongguancun Lab), Chuanpu Fu (Tsinghua University), Guangmeng Zhou (Tsinghua University), Ke Xu (Tsinghua University and Zhongguancun Lab)

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 an 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.

View More Papers

On Borrowed Time: Measurement-Informed Understanding of the NTP Pool's...

Robert Beverly (San Diego State University), Erik Rye (Johns Hopkins University)

Read More

TYPEFUZZ: Type Coverage Directed JavaScript Engine Fuzzing (Registered Report)

Tobias Wienand (Ruhr-Universitat Bochum), Lukas Bernhard (Ruhr-Universitat Bochum), Flavio Toffalini (Ruhr-Universitat Bochum)

Read More

Rounding-Guided Backdoor Injection in Deep Learning Model Quantization

Xiangxiang Chen (Zhejiang University), Peixin Zhang (Singapore Management University), Jun Sun (Singapore Management University), Wenhai Wang (Zhejiang University), Jingyi Wang (Zhejiang University)

Read More