LLM Security Guard for Code

Authors: Arya Kavian, Mohammad Mehdi Pourhashem Kallehbasti, Sajjad Kazemi, Ehsan Firouzi, Mohammad Ghafari
Published: 2024-05-02 | Updated: 2024-05-03

Source: https://arxiv.org/abs/2405.01103

PDF: https://arxiv.org/pdf/2405.01103

AIにより推定されたラベル

LLMセキュリティ プロンプトインジェクション セキュリティ分析

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

Many developers rely on Large Language Models (LLMs) to facilitate software development. Nevertheless, these models have exhibited limited capabilities in the security domain. We introduce LLMSecGuard, a framework to offer enhanced code security through the synergy between static code analyzers and LLMs. LLMSecGuard is open source and aims to equip developers with code solutions that are more secure than the code initially generated by LLMs. This framework also has a benchmarking feature, aimed at providing insights into the evolving security attributes of these models.