SecCodeBench is a benchmark suite for evaluating the security of AI-generated code, specifically designed for modern Agentic Coding Tool. It is jointly developed by Alibaba Group in collaboration with ...
CGBridge is a novel framework designed to enhance the code understanding capabilities of Large Language Models (LLMs) by integrating rich structural information from code graphs. Our approach follows ...
Abstract: Starting with the pandemic, and then amplified by the launch of publicly available large language models like ChatGPT, which are capable to generate snippets of code for different tasks ...
Abstract: Deep code models are vulnerable to adversarial attacks, making it possible for semantically identical inputs to trigger different responses. Current black-box attack methods typically ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback