Zhengxiong Luo (Tsinghua University), Kai Liang (Central South University), Yanyang Zhao (Tsinghua University), Feifan Wu (Tsinghua University), Junze Yu (Tsinghua University), Heyuan Shi (Central South University), Yu Jiang (Tsinghua University)

Automatic protocol reverse engineering is essential for various security applications. While many existing techniques achieve this task by analyzing static network traces, they face increasing challenges due to their dependence on high-quality samples. This paper introduces DynPRE, a protocol reverse engineering tool that exploits the interactive capabilities of protocol servers to obtain more semantic information and additional traffic for dynamic inference. DynPRE first processes the initial input network traces and learns the rules for interacting with the server in different contexts based on session-specific identifier detection and adaptive message rewriting. It then applies exploratory request crafting to obtain semantic information and supplementary samples and performs real-time analysis. Our evaluation on 12 widely used protocols shows that DynPRE identifies fields with a perfection score of 0.50 and infers message types with a V-measure of 0.94, significantly outperforming state-of-the-art methods like Netzob, Netplier, FieldHunter, BinaryInferno, and Nemesys, which achieve average perfection and V-measure scores of (0.15, 0.72), (0.16, 0.73), (0.15, 0.83), (0.15, -), and (0.31, -), respectively. Furthermore, case studies on unknown protocols highlight the effectiveness of DynPRE in real-world applications.

View More Papers

WIP: Savvy: Trustworthy Autonomous Vehicles Architecture

Ali Shoker, Rehana Yasmin, Paulo Esteves-Verissimo (Resilient Computing & Cybersecurity Center (RC3), KAUST)

Read More

Free Proxies Unmasked: A Vulnerability and Longitudinal Analysis of...

Naif Mehanna (Univ. Lille / Inria / CNRS), Walter Rudametkin (IRISA / Univ Rennes), Pierre Laperdrix (CNRS, Univ Lille, Inria Lille), and Antoine Vastel (Datadome)

Read More

Strengthening Privacy in Robust Federated Learning through Secure Aggregation

Tianyue Chu, Devriş İşler (IMDEA Networks Institute & Universidad Carlos III de Madrid), Nikolaos Laoutaris (IMDEA Networks Institute)

Read More

HEIR: A Unified Representation for Cross-Scheme Compilation of Fully...

Song Bian (Beihang University), Zian Zhao (Beihang University), Zhou Zhang (Beihang University), Ran Mao (Beihang University), Kohei Suenaga (Kyoto University), Yier Jin (University of Science and Technology of China), Zhenyu Guan (Beihang University), Jianwei Liu (Beihang University)

Read More