We have a technical paper [1] and a tool demonstration paper [2] accepted at ASE’24. The first paper presents an empirical study evaluating existing AIGC detectors in the software domain. Despite its potential, the misuse of LLMs, especially in security and safety-critical domains, such as academic integrity and answering questions on Stack Overflow, poses significant concerns. In the second paper, we introduce OpenTracer, which offers comprehensive tracking of complete transaction information to extract user-desired data such as invariant-related data. OpenTracer has been employed to analyze 350,800 Ethereum transactions, successfully inferring 23 different types of invariant from predefined templates. OpenTracer is open-source and a video demostration can be found below.
OpenTracer Demo Video
This year, 118 out of 587 submissions were accepted (another 37 were conditionally accepted) at ASE, which gives an acceptance rate of 27.3%.
References
- Wang, J., Liu, S., Xie, X., & Li, Y. (2024). An Empirical Study to Evaluate AIGC Detectors on Code Content. Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering (ASE), 844–856.
- Chen, Z., Liu, Y., Beillahi, S. M., Li, Y., & Long, F. (2024). OpenTracer: A Dynamic Transaction Trace Analyzer for Smart Contract Invariant Generation and Beyond. Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2399–2402.