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

How to Effectively Trace Provenance on Windows Endpoint Detection...

Jason Liu (University of Illinois at Urbana-Champaign), Muhammad Adil Inam (University of Illinois at Urbana-Champaign), Akul Goyal (University of Illinois at Urbana-Champaign), Dylen Greenenwald (University of Illinois at Urbana-Champaign), Adam Bates (University of Illinois at Urbana-Champaign), Saurav Chittal (Purdue University)

Read More

User-Space Dependency-Aware Rehosting for Linux-Based Firmware Binaries

Chuan Qin (Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences; Nanyang Technological University), Cen Zhang (Nanyang Technological University), Yaowen Zheng (Institute of Information Engineering, Chinese Acadamy of Sciences), Puzhuo Liu (Ant Group; Tsinghua University), Jian Zhang (Nanyang Technological University), Yeting Li (Institute of Information Engineering,…

Read More

Distributed Broadcast Encryption for Confidential Interoperability across Private Blockchains

Angelo De Caro (IBM Research Zurich), Kaoutar Elkhiyaoui (IBM Research Zurich), Sandeep Nishad (IBM Research India), Sikhar Patranabis (IBM Research India), Venkatraman Ramakrishna (IBM Research India)

Read More