English

CoGate: Confidence-Gated Co-Decoding for Secure Code Generation

Software Engineering 2026-07-30 v1

Abstract

Large language models are widely used for code generation, but they can also produce insecure programs due to patterns learned from their pretraining data. Decoding-time steering has become an important solution to this problem: a small expert model is combined with the target model at each step to generate more secure code, which is referred to as co-decoding. However, the acceptance rule for existing co-decoding approaches does not consider the expert model's confidence. When the security expert is unconfident due to unseen patterns or out-of-distribution (OOD) contexts, its guidance can therefore be misleading. To address the challenge, we propose CoGate, a confidence-gated co-decoding approach that controls the expert's influence on the co-decoding process based on its confidence. We implement our approach and evaluate it across multiple LLM backends (CodeGen, DeepSeek-Coder, Qwen-Coder, StarCoder) on several code generation benchmarks (HumanEval, security suite, and CWEval). Our approach outperforms existing co-decoding methods (CoSec+) across multiple benchmarks, achieving up to a 12.6% gain of Func-Sec@10 on CWEval.

Cite

@article{arxiv.2607.28529,
  title  = {CoGate: Confidence-Gated Co-Decoding for Secure Code Generation},
  author = {Minghao Hu and Lannan Luo and Allen Roush and Phillip Howard},
  journal= {arXiv preprint arXiv:2607.28529},
  year   = {2026}
}