We have three technical papers and a tool demonstration paper accepted at ASE’25:
- Defects4C [1]: The first major benchmark for evaluating LLMs on fixing real-world C/C++ bugs, closing a crucial gap in automated program repair.
- DeFiScope [2]: An LLM-powered detector that finds DeFi price manipulation attacks with 96% precision, uncovering 81 previously unknown incidents.
- Co^2FuLL [3]: Makes binary code analysis accurate and explainable by fusing context with content and using LLMs for verification, boosting precision by 142.5%.
- DeepTx [4]: A real-time Web3 transaction shield that uses multi-modal LLM reasoning to stop phishing attacks before they happen.
DeepTx is open-source and a video demostration can be found below:
DeepTx Demo Video
This year, ASE received 1190 submissions and 1136 were remaining after desk rejection. Out of the 1136 submissions, 113 papers were directly accepted and 132 were accepted after major revisions, which gives an overall acceptance rate of 21.6%.
References
- Wang, J., Xie, X., Hu, Q., Liu, S., Yu, J., Kong, J., & Li, Y. (2025, November). Defects4C: Benchmarking Large Language Model Repair Capability with C/C++ Bugs. Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE).
- Zhong, J., Wu, D., Liu, Y., Xie, M., Liu, Y., Li, Y., & Liu, N. (2025, November). Detecting Various DeFi Price Manipulations with LLM Reasoning. Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE).
- Dong, C., Guo, J., Yang, S., Li, Y., Fang, D., Xiao, Y., Chen, Y., & Sun, L. (2025, November). Advancing Binary Code Similarity Detection via Context-Content Fusion and LLM Verification. Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE).
- Liu, Y., Li, X., & Li, Y. (2025, November). DeepTx: Real-Time Transaction Risk Analysis via Multi-Modal Features and LLM Reasoning. Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE).