[new-research] arXiv:2604.09089 — DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation

[github-actions]

New arXiv Research Paper

arXiv ID: 2604.09089
Title: DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation
Authors: Li Huang, Zhongxin Liu, Yifan Wu, Tao Yin, Dong Li, Jichao Bi, Nankun Mu, Hongyu Zhang, Meng Yan
Published: 2026-04-10T08:19:48Z
URL: https://arxiv.org/abs/2604.09089

Abstract (first 300 chars)

Large Language Models (LLMs) for code generation can replicate insecure patterns from their training data. To mitigate this, a common strategy for security hardening is to fine-tune models using supervision derived from the final transformer layer. However, this design may suffer from a final-layer …

Suggested OWASP Mapping

DSGAI04, LLM03

Suggested Action

Review this paper against the GenAI Security Crosswalk entries and update relevant mapping files if new attack patterns or mitigations are identified.