Vul-4J
Emerging6papers using it
2023first seen
The Vul-4J dataset is a benchmark containing 64 Java vulnerabilities used to evaluate the effectiveness of Large Language Models in generating automated security patches.
Papers using Vul-4J (6)
- Leveraging GPT-4 for Vulnerability-Witnessing Unit Test GenerationIdentifying Helpful Context for LLM-based Vulnerability Repair: A Preliminary StudyWhy LLMs Fail: A Failure Analysis and Partial Success Measurement for Automated Security Patch GenerationRepairing vulnerabilities without invisible hands. A differentiated replication study on LLMsHow Effective Are Neural Networks for Fixing Security VulnerabilitiesThere are More Fish in the Sea: Automated Vulnerability Repair via
Binary Templates