The authors constructed a security suite with 4 security tasks covering various vulnerability types.
Training recipe boosts security in AI-generated code by improving planning and testing
SECUREVIBE uses supervised fine-tuning and post-training to enhance security behaviors, outperforming baselines on multiple benchmarks.
Big Tech
Danqing Wang · Baolin Peng · Zhepei Wei · Isadora White · Wenlin Yao · Hao Cheng · +5 more
Carnegie Mellon University · Microsoft Research · University of Virginia · University of California, San Diego
Research Digest··2 min read
Thread:Agent Security & Attacks
The authors developed SECUREVIBE, a training recipe that explicitly targets planning and testing for code security.
Why this paper
From Microsoft Research and 3 others · Part of Agent Security & Attacks, now 43 papers
In one line
SecureVibe improves code security in vibe coding by training agents to plan and test for security, boosting security pass@1 by 6.9 points.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (3 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§