Sima Arasteh (University of Southern California), Pegah Jandaghi, Nicolaas Weideman (University of Southern California/Information Sciences Institute), Dennis Perepech, Mukund Raghothaman (University of Southern California), Christophe Hauser (Dartmouth College), Luis Garcia (University of Utah Kahlert School of Computing)

The software compilation process has a tendency to obscure the original design of the system and makes it difficult both to identify individual components and discern their purpose simply by examining the resulting binary code. Although decompilation techniques attempt to recover higherlevel source code from the machine code in question, they are not fully able to restore the semantics of the original functions. Furthermore, binaries are often stripped of metadata, and this makes it challenging to reverse engineer complex binary software.
In this paper we show how a combination of binary decomposition techniques, decompilation passes, and LLM-powered function summarization can be used to build an economical engine to identify modules in stripped binaries and associate them with high-level natural language descriptions. We instantiated this technique with three underlying open-source LLMs—CodeQwen, DeepSeek-Coder and CodeStral—and measured its effectiveness in identifying modules in robotics firmware. This experimental evaluation involved 467 modules from four devices from the ArduPilot software suite, and showed that CodeStral, the bestperforming backend LLM, achieves an average F1-score of 0.68 with an online running time of just a handful of seconds.

View More Papers

Generating API Parameter Security Rules with LLM for API...

Jinghua Liu (Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China; School of Cyber Security, University of Chinese Academy of Sciences, China), Yi Yang (Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China; School of Cyber Security, University of Chinese Academy of Sciences, China), Kai Chen (Institute of Information Engineering, Chinese Academy of…

Read More

It Doesn’t Have to Be So Hard: Efficient Symbolic...

Vaibhav Sharma (University of Minnesota), Navid Emamdoost (University of Minnesota), Seonmo Kim (University of Minnesota), Stephen McCamant (University of Minnesota)

Read More

EvoCrawl: Exploring Web Application Code and State using Evolutionary...

Xiangyu Guo (University of Toronto), Akshay Kawlay (University of Toronto), Eric Liu (University of Toronto), David Lie (University of Toronto)

Read More

Towards LLM-Assisted Vulnerability Detection and Repair for Open-Source 5G...

Rupam Patir (University at Buffalo), Qiqing Huang (University at Buffalo), Keyan Guo (University at Buffalo), Wanda Guo (Texas A&M University), Guofei Gu (Texas A&M University), Haipeng Cai (University at Buffalo), Hongxin Hu (University at Buffalo)

Read More