New ML tool Ruby unmasks unsafe Rust code in binaries

Researchers have developed Ruby, a novel machine learning tool designed to identify unsafe code regions within stripped Rust binaries. Unlike previous tools that require source code access, Ruby analyzes binary instructions to pinpoint these safety-critical areas. In evaluations, Ruby successfully identified 91.75% of unsafe regions with a low false positive rate of 6.16%, outperforming leading LLMs like GPT-5.2, Claude-4.5, and Gemini-3. The tool has also demonstrated practical utility by accelerating symbolic execution and fuzzing, leading to the discovery and patching of five bugs in Android libraries by Google. AI

IMPACT Enhances security analysis of compiled code, potentially improving software safety and bug detection in systems like Android.

RANK_REASON Academic paper detailing a new ML tool for binary analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• android
• claude-4.5
• Gemini 3
• Google
• GPT-5.2
• Ruby
• Rust
• SangDon Park

• paper
• product
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →