ZGZeyu Gao

Zeyu Gao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zeyu Gao has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    PCodeTrans: Translate Decompiled Pseudocode to Trace-Level Equivalent Source Code

    by Yuxin Cui, Zeyu Gao, Siliang Qin, Yuanda Wang, Jiaming Wang, Xize Luo, Peng Zhou, Chao Zhang

  • Open Access

    Are Reasoning Traces Faithful in LLM-Based Code Vulnerability Detection?

    by Jialai Wang, Juncheng Lu, Songtao Yang, Bingyi He, Zeyu Gao, Chao Zhang, Shuai Wang

  • Open Access

    ProgSCA: Software Composition Analysis via Program-Level Modeling

    by Peihong Li, Cheng Li, Yuchen Gu, Yanzhe Hu, Liheng Chen, Zeyu Gao, Hao Wang, Chao Zhang

    Software composition analysis (SCA) aims to identify third-party dependencies in programs, which plays a critical role in ensuring software supply chain security. Existing approaches largely follow a rule-based paradigm: they first compute function-level similarities, then aggregate these results using handcrafted heuristics to determine which third-party libraries (TPLs) the target program depends on. However, such rules require substantial manual effort and expert knowledge to design, tune, and maintain. To address this, we present ProgSCA, an SCA framework based on a two-stage strategy and program-level rather than function-level modeling. ProgSCA formulates SCA as a retrieval problem, first employing lightweight methods to quickly filter out irrelevant libraries from numerous candidate TPLs, then using a model trained at the program level to directly predict dependency between programs. Comprehensive evaluations show that ProgSCA achieves state-of-the-art performance in SCA tasks, improving F1 scores over existing methods by 174% and 100% in two mainstream scenarios, respectively. Moreover, ProgSCA maintains a consistent advantage across different datasets and different candidate pool scales, and also proves effective in the downstream task of function similarity matching, further demonstrating the practical value of our approach.

  • Open Access

    AID: Lightweight Disassembly via Learning-Superset-Learning-Recursive Algorithm

    by Yuchen Zhou, Hao Wang, Zeyu Gao, Chao Zhang, Xi Xiao

    Disassembly remains the foundation of binary analysis tasks but continues to face many significant challenges that hurt precision, recall, or speed. In this paper, we propose a lightweight disassembly approach called AID that strikes an effective balance between precision, recall, and speed. At the core, it first fuses superset disassembly and a learning-based approach to identify potential code entries with high recall and precision. Then it uses recursive disassembly to recover instructions with high precision. We implemented a prototype of AID and evaluated it across various datasets, including real-world binaries, large-size binaries, and complex binaries. Experiments demonstrate that AID delivers exceptional performance in terms of speed, precision, and recall. Its speed is comparable to that of IDA Pro and DeepDi, but significantly faster than Angr, Ddisasm, Ghidra, and DASSA. On the SPEC2017 dataset, AID reduces missed instructions (i.e., false negatives) by 1.68 to 148 times compared to baselines and reduces erroneous instructions (i.e., false positives) by 1.49 to 1,243 times.

  • Top Cited Papers
    Open Access

    HyRES : Recovering Data Structures in Binaries via Semantic Enhanced Hybrid Reasoning

    by Zihan Sha, Hui Shu, Hao Wang, Zeyu Gao, Yang Lan, Chao Zhang

    Binary reverse engineering is pivotal in the realm of cybersecurity, enabling critical applications such as malware analysis, legacy code hardening, and vulnerability detection. However, the challenge of recovering structural information from binaries, especially stripped ones, persists due to the significant loss of variable boundaries, types, names, and dataflow information during compilation. In this article, we introduce Hy brid RE asoning for S tructure Recovery ( HyRES ), an innovative hybrid reasoning technique that energizes static analysis, Large Language Model (LLM), and heuristic methods to recover data structures from stripped binaries. It analyzes the structure layout and proficiently infer its semantics via LLM, and utilizes semantics to perform semantic-enhanced structure aggregation, which overcomes the need for complete dataflow. HyRES outperforms State-of-the-Art (SOTA) solutions in terms of structure pointer identification and layout recovery. Specifically, HyRES achieves 65.1% higher recall and 33.4% higher accuracy than the SOTA, while also being 64.2% faster than existing SOTA solutions. Comprehensive experiments demonstrate HyRES ’s superior performance and practical utility in real-world reverse engineering tasks, marking a significant advancement in binary analysis.


  • Open Access

    BinQuery: A Novel Framework for Natural Language-Based Binary Code Retrieval

    by Bolun Zhang, Zeyu Gao, Hao Wang, Yuxin Cui, Siliang Qin, Chao Zhang, Kai Chen, Beibei Zhao

    Binary Function Retrieval (BFR) is crucial in reverse engineering for identifying specific functions in binary code, especially those associated with malicious behavior or vulnerabilities. Traditional BFR methods rely on heuristics, often lacking the efficiency and adaptability needed for large-scale or diverse binary analysis tasks. To address these challenges, we present BinQuery, a Natural Language-based BFR (NL-based BFR) framework that uses natural language queries to retrieve relevant binary functions with improved flexibility and precision. BinQuery introduces innovative techniques to bridge information gaps between binary code and natural language, achieves fine-grained alignment for enhanced retrieval accuracy, and leverages Large Language Models (LLMs) to refine queries and generate diverse descriptions. Our extensive experiments indicate that BinQuery surpasses current state-of-the-art methods, achieving a 42.55% increase in recall@1 and a 4× improvement in performance on comparable benchmarks.


  • Open Access

    llasm: Naming Functions in Binaries by Fusing Encoder-only and Decoder-only LLMs

    by Zihan Sha, Hao Wang, Zeyu Gao, Hui Shu, Bolun Zhang, Ziqing Wang, Chao Zhang

    Predicting function names in stripped binaries, which requires succinctly summarizing semantics of binary code in natural languages, is a crucial but challenging task. Recently, many machine learning based solutions have been proposed. However, they have poor generalizability, i.e., fail to handle unseen binaries. To advance the state of the art, we present large assembly language Model ( llasm ) , a novel framework which fuses encoder-only and decoder-only LLMs for function name prediction. It refines encoder-only models to preserve more binary information and learn better binary representations. Then it adopts a novel architecture to project the encoding to the input space of a decoder-only natural language model, which enables it to have better capability of inferring general knowledge and better generalizability. We have evaluated llasm in the BinaryCorp and Debin datasets. llasm outperforms the state-of-the-art function name prediction tools by up to 19.9%, 40.7%, and 36.5% in precision, recall, and F1 score, with significantly better generalizability in unseen binaries. Our case studies further demonstrate the practical use cases of llasm in analyzing real-world malware, showing the usefulness of function name prediction.


  • Open Access

    CEBin: A Cost-Effective Framework for Large-Scale Binary Code Similarity Detection

    by Hao Wang, Zeyu Gao, Chao Zhang, Mingyang Sun, Yuchen Zhou, Han Qiu, Xi Xiao

    Binary code similarity detection (BCSD) is a fundamental technique for various applications. Many BCSD solutions have been proposed recently, which mostly are embedding-based, but have shown limited accuracy and efficiency especially when the volume of target binaries to search is large. To address this issue, we propose a cost-effective BCSD framework, CEBin, which fuses embedding-based and comparison-based approaches to significantly improve accuracy while minimizing overheads. Specifically, CEBin utilizes a refined embedding-based approach to extract features of target code, which efficiently narrows down the scope of candidate similar code and boosts performance. Then, it utilizes a comparison-based approach that performs a pairwise comparison on the candidates to capture more nuanced and complex relationships, which greatly improves the accuracy of similarity detection. By bridging the gap between embedding-based and comparison-based approaches, CEBin is able to provide an effective and efficient solution for detecting similar code (including vulnerable ones) in large-scale software ecosystems. Experimental results on three well-known datasets demonstrate the superiority of CEBin over existing state-of-the-art (SOTA) baselines. To further evaluate the usefulness of BCSD in real world, we construct a large-scale benchmark of vulnerability, offering the first precise evaluation scheme to assess BCSD methods for the 1-day vulnerability detection task. CEBin could identify the similar function from millions of candidate functions in just a few seconds and achieves an impressive recall rate of 85.46% on this more practical but challenging task, which are several order of magnitudes faster and 4.07× better than the best SOTA baseline.


  • Open Access

    CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision

    by Hao Wang, Zeyu Gao, Chao Zhang, Zihan Sha, Mingyang Sun, Yuchen Zhou, Wenyu Zhu, Wenju Sun, Han Qiu, Xi Xiao

    Binary code representation learning has shown significant performance in binary analysis tasks. But existing solutions often have poor transferability, particularly in few-shot and zero-shot scenarios where few or no training samples are available for the tasks. To address this problem, we present CLAP (Contrastive Language-Assembly Pre-training), which employs natural language supervision to learn better representations of binary code (i.e., assembly code) and get better transferability. At the core, our approach boosts superior transfer learning capabilities by effectively aligning binary code with their semantics explanations (in natural language), resulting a model able to generate better embeddings for binary code. To enable this alignment training, we then propose an efficient dataset engine that could automatically generate a large and diverse dataset comprising of binary code and corresponding natural language explanations. We have generated 195 million pairs of binary code and explanations and trained a prototype of CLAP. The evaluations of CLAP across various downstream tasks in binary analysis all demonstrate exceptional performance. Notably, without any task-specific training, CLAP is often competitive with a fully supervised baseline, showing excellent transferability.