CodeHacker: Automated Test Case Generation for Detecting Vulnerabilities in Competitive Programming Solutions
This addresses the need for more robust evaluation of code generation models in competitive programming, though it is an incremental improvement over existing methods.
The paper tackles the problem of insufficient test case coverage in evaluating LLM-generated code by proposing CodeHacker, an automated framework that generates adversarial test cases to detect vulnerabilities in competitive programming solutions, resulting in a significant improvement in True Negative Rate for filtering incorrect solutions.
The evaluation of Large Language Models (LLMs) for code generation relies heavily on the quality and robustness of test cases. However, existing benchmarks often lack coverage for subtle corner cases, allowing incorrect solutions to pass. To bridge this gap, we propose CodeHacker, an automated agent framework dedicated to generating targeted adversarial test cases that expose latent vulnerabilities in program submissions. Mimicking the hack mechanism in competitive programming, CodeHacker employs a multi-strategy approach, including stress testing, anti-hash attacks, and logic-specific targeting to break specific code submissions. To ensure the validity and reliability of these attacks, we introduce a Calibration Phase, where the agent iteratively refines its own Validator and Checker via self-generated adversarial probes before evaluating contestant code.Experiments demonstrate that CodeHacker significantly improves the True Negative Rate (TNR) of existing datasets, effectively filtering out incorrect solutions that were previously accepted. Furthermore, generated adversarial cases prove to be superior training data, boosting the performance of RL-trained models on benchmarks like LiveCodeBench.