DLInfer: Deep Learning with Static Slicing for Python Type Inference

Yan, Yanyan; Feng, Yang; Fan, Hongcheng; Xu, Baowen

doi:10.1109/icse48619.2023.00170

Cited by 5 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the deep learning techniques having demonstrated remarkable performance in addressing a variety of program analysis challenges [23][24][25], several studies [4,26] have also been proposed that leverage deep neural networks to identify compilation details. BinEye [16] is such an initial work, which employs instruction embeddings and CNNs to recognize the optimization levels for each object file.…”

Section: Learning-based Approachesmentioning

confidence: 99%

Function-Level Compilation Provenance Identification with Multi-Faceted Neural Feature Distillation and Fusion

Gao,

Liang,

et al. 2024

Electronics

View full text Add to dashboard Cite

In the landscape of software development, the selection of compilation tools and settings plays a pivotal role in the creation of executable binaries. This diversity, while beneficial, introduces significant challenges for reverse engineers and security analysts in deciphering the compilation provenance of binary code. To this end, we present MulCPI, short for Multi-representation Fusion-based Compilation Provenance Identification, which integrates the features collected from multiple distinct intermediate representations of the binary code for better discernment of the fine-grained function-level compilation details. In particular, we devise a novel graph-oriented neural encoder improved upon the gated graph neural network by subtly introducing an attention mechanism into the neighborhood nodes’ information aggregation computation, in order to better distill the more informative features from the attributed control flow graph. By further integrating the features collected from the normalized assembly sequence with an advanced Transformer encoder, MulCPI is capable of capturing a more comprehensive set of features manifesting the multi-faceted lexical, syntactic, and structural insights of the binary code. Extensive evaluation on a public dataset comprising 854,858 unique functions demonstrates that MulCPI exceeds the performance of current leading methods in identifying the compiler family, optimization level, compiler version, and the combination of compilation settings. It achieves average accuracy rates of 99.3%, 96.4%, 90.7%, and 85.3% on these tasks, respectively. Additionally, an ablation study highlights the significance of MulCPI’s core designs, validating the efficiency of the proposed attention-enhanced gated graph neural network encoder and the advantages of incorporating multiple code representations.

show abstract

Section: Learning-based Approachesmentioning

confidence: 99%

Function-Level Compilation Provenance Identification with Multi-Faceted Neural Feature Distillation and Fusion

Gao,

Liang,

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…DLInfer [Y. Yan et al, 2023] uses static slicing to isolate variable usages before training a deep neural network. Ye, Zhao, Shirako, et al [2023] use a combination of machine learning and SMT constraint solving to infer types, but their end goal is code optimization, not type migration.…”

Section: Pythonmentioning

confidence: 99%

Predicting typeScript type annotations and definitions with machine learning

Yee

View full text Add to dashboard Cite

This has been a very long journey, and there have been so many days, weeks, and months where I did not think I would ever reach the end. But I made it, thanks to everyone who has supported and encouraged me.First, I have to thank my advisor, Arjun Guha. I genuinely believe I would not have completed my Ph.D. without Arjun. My committee, Michael Greenberg, Frank Tip, and Steven Holtzen, also helped me get over the finish line, with their thoughtful feedback and questions.I had the opportunity to mentor and advise several undergraduate and master's students. Thank you for being great collaborators. I learned a lot from

show abstract

DyPyBench: A Benchmark of Executable Python Software

Bouzenia,

Krishan,

Pradel

2024

Proc. ACM Softw. Eng.

View full text Add to dashboard Cite

Python has emerged as one of the most popular programming languages, extensively utilized in domains such as machine learning, data analysis, and web applications. Python’s dynamic nature and extensive usage make it an attractive candidate for dynamic program analysis. However, unlike for other popular languages, there currently is no comprehensive benchmark suite of executable Python projects, which hinders the development of dynamic analyses. This work addresses this gap by presenting DyPyBench, the first benchmark of Python projects that is large-scale, diverse, ready-to-run (i.e., with fully configured and prepared test suites), and ready- to-analyze (by integrating with the DynaPyt dynamic analysis framework). The benchmark encompasses 50 popular open-source projects from various application domains, with a total of 681k lines of Python code, and 30k test cases. DyPyBench enables various applications in testing and dynamic analysis, of which we explore three in this work: (i) Gathering dynamic call graphs and empirically comparing them to statically computed call graphs, which exposes and quantifies limitations of existing call graph construction techniques for Python. (ii) Using DyPyBench to build a training data set for LExecutor, a neural model that learns to predict values that otherwise would be missing at runtime. (iii) Using dynamically gathered execution traces to mine API usage specifications, which establishes a baseline for future work on specification mining for Python. We envision DyPyBench to provide a basis for other dynamic analyses and for studying the runtime behavior of Python code.

show abstract

DLInfer: Deep Learning with Static Slicing for Python Type Inference

Cited by 5 publications

References 40 publications

Function-Level Compilation Provenance Identification with Multi-Faceted Neural Feature Distillation and Fusion

Function-Level Compilation Provenance Identification with Multi-Faceted Neural Feature Distillation and Fusion

Predicting typeScript type annotations and definitions with machine learning

DyPyBench: A Benchmark of Executable Python Software

Contact Info

Product

Resources

About