🏆 JsDeObsBench Leaderboard 🏆

JsDeObsBench: Measuring and Benchmarking LLMs for JavaScript Deobfuscation

Guoqiang Chen, Xin Jin, Zhiqiang Lin

📢 News: To submit new evaluation results, please create a pull request in the repository!

github paper javascript

📝 Notes

  1. The single and combination tags present the deobfuscation results against one transformation and combined transformations, respectively.
  2. Models are ranked according to overall score by default, which is an average of four metrics. More details about the metrics can be found in our paper.
  3. 🎓 marks models designed for JavaScript deobfuscation, namely expert models, and the others are standard models.
  4. "Size" here is the amount of overall model weight.
  5. Model providers have the responsibility to avoid data contamination. Models trained on close data can be affected by contamination.
  6. Please use our benchmark repository to perform a new evaluation of your method and request to merge the results into this leaderboard.

📖 BibTeX

@inproceedings{jsdeobfbench-2025ccs,
 title={JsDeObsBench: Measuring and Benchmarking LLMs for JavaScript Deobfuscation},
 author={Guoqiang Chen and Xin Jin and Zhiqiang Lin},
 booktitle = {Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security (CCS)},
 year={2025}
}