Responsibility & Safety Introducing CodeMender: an AI agent for code security Share
Copy link ×
Using advanced AI to fix critical software vulnerabilities Today, we’re sharing early results from our research on CodeMender, a new AI-powered agent that improves code security automatically. Software vulnerabilities are notoriously difficult and time-consuming for developers to find and fix, even with traditional, automated methods like fuzzing. Our AI-based efforts like Big Sleep and OSS-Fuzz have demonstrated AI’s ability to find new zero-day vulnerabilities in well-tested software. As we achieve more breakthroughs in AI-powered vulnerability discovery, it will become increasingly difficult for humans alone to keep up. CodeMender helps solve this problem by taking a comprehensive approach to code security that’s both reactive, instantly patching new vulnerabilities, and proactive, rewriting and securing existing code and eliminating entire classes of vulnerabilities in the process. Over the past six months that we’ve been building CodeMender, we have already upstreamed 72 security fixes to open source projects, including some as large as 4.5 million lines of code. By automatically creating and applying high-quality security patches, CodeMender’s AI-powered agent helps developers and maintainers focus on what they do best — building good software. CodeMender in action CodeMender operates by leveraging the thinking capabilities of recent Gemini Deep Think models to produce an autonomous agent capable of debugging and fixing complex vulnerabilities. To do this, the CodeMender agent is equipped with robust tools that let it reason about code before making changes, and automatically validate those changes to make sure they’re correct and don’t cause regressions.
Pause video Play video
While large language models are rapidly improving, mistakes in code security could be costly. CodeMender’s automatic validation process ensures that code changes are correct across many dimensions by only surfacing for human review high-quality patches that, for example, fix the root cause of the issue, are functionally correct, cause no regressions and follow style guidelines. As part of our research, we also developed new techniques and tools that let CodeMender reason about code and validate changes more effectively. This includes: Advanced program analysis: We developed tools based on advanced program analysis that include static analysis, dynamic analysis, differential testing, fuzzing and SMT solvers. Using these tools to systematically scrutinize code patterns, control flow and data flow, CodeMender can better identify the root causes of security flaws and architectural weaknesses.
We developed tools based on advanced program analysis that include static analysis, dynamic analysis, differential testing, fuzzing and SMT solvers. Using these tools to systematically scrutinize code patterns, control flow and data flow, CodeMender can better identify the root causes of security flaws and architectural weaknesses. Multi-agent systems: We developed special-purpose agents that enable CodeMender to tackle specific aspects of an underlying problem. For example, CodeMender uses a large language model-based critique tool that highlights the differences between the original and modified code in order to verify that the proposed changes do not introduce regressions, and self-correct as needed. Fixing vulnerabilities To effectively patch a vulnerability, and prevent it from re-emerging, Code Mender uses a debugger, source code browser, and other tools to pinpoint root causes and devise patches. We have added two examples of CodeMender patching vulnerabilities in the video carousel below. Example #1: Identifying the root cause of a vulnerability Here’s a snippet of the agent's reasoning about the root cause for a CodeMender-generated patch, after analyzing the results of debugger output and a code search tool. Although the final patch in this example only changed a few lines of code, the root cause of the vulnerability was not immediately clear. In this case, the crash report showed a heap buffer overflow, but the actual problem was elsewhere — an incorrect stack management of Extensible Markup Language (XML) elements during parsing. Example #2: Agent is able to create non-trivial patches In this example, the CodeMender agent was able to come up with a non-trivial patch that deals with a complex object lifetime issue. The agent was not only able to figure out the root cause of the vulnerability, but was also able to modify a completely custom system for generating C code within the project.
Pause video Play video Pause video Play video
... continue reading