Search papers, labs, and topics across Lattice.
The paper introduces TOSSS, a new benchmark for evaluating LLMs' ability to distinguish between secure and vulnerable code snippets, using data from the CVE database. TOSSS provides a security score between 0 and 1, reflecting the model's preference for secure code. Experiments on 14 open-source and closed-source models across C/C++ and Java reveal scores ranging from 0.48 to 0.89, highlighting the varying security awareness of different LLMs.
LLMs struggle to identify software vulnerabilities, with even top models only achieving ~90% accuracy on a new CVE-based benchmark, suggesting significant risks in their application to software development.
With their increasing capabilities, Large Language Models (LLMs) are now used across many industries. They have become useful tools for software engineers and support a wide range of development tasks. As LLMs are increasingly used in software development workflows, a critical question arises: are LLMs good at software security? At the same time, organizations worldwide invest heavily in cybersecurity to reduce exposure to disruptive attacks. The integration of LLMs into software engineering workflows may introduce new vulnerabilities and weaken existing security efforts. We introduce TOSSS (Two-Option Secure Snippet Selection), a benchmark that measures the ability of LLMs to choose between secure and vulnerable code snippets. Existing security benchmarks for LLMs cover only a limited range of vulnerabilities. In contrast, TOSSS relies on the CVE database and provides an extensible framework that can integrate newly disclosed vulnerabilities over time. Our benchmark gives each model a security score between 0 and 1 based on its behavior; a score of 1 indicates that the model always selects the secure snippet, while a score of 0 indicates that it always selects the vulnerable one. We evaluate 14 widely used open-source and closed-source models on C/C++ and Java code and observe scores ranging from 0.48 to 0.89. LLM providers already publish many benchmark scores for their models, and TOSSS could become a complementary security-focused score to include in these reports.
