DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation

Computer Science > Software Engineering [Submitted on 10 Apr 2026] DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation Li Huang, Zhongxin Liu, Yifan Wu, Tao Yin, Dong Li, Jichao Bi, Nankun Mu, Hongyu Zhang, Meng Yan 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 bottleneck: vulnerability-discriminative cues can be distributed across layers and become less detectable near the output representations optimized for next-token prediction. To diagnose this issue, we perform layer-wise linear probing. We observe that vulnerability-related signals are most detectable in a band of intermediate-to-upper layers yet attenuate toward the final layers. Motivated by this observation, we introduce DeepGuard, a framework that leverages distributed security-relevant cues by aggregating representations from multiple upper layers via an attention-based module. The aggregated signal powers a dedicated security analyzer within a multi-objective training objective that balances security enhancement and functional correctness, and further supports a lightweight inference-time steering strategy. Extensive experiments across five code LLMs demonstrate that DeepGuard improves the secure-and-correct generation rate by an average of 11.9% over strong baselines such as SVEN. It also preserves functional correctness while exhibiting generalization to held-out vulnerability types. Our code is public at this https URL. Comments: ACL 2026 main conference Subjects: Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR) Cite as: arXiv:2604.09089 [cs.SE]   (or arXiv:2604.09089v1 [cs.SE] for this version)   https://doi.org/10.48550/arXiv.2604.09089 Focus to learn more Submission history From: Li Huang [view email] [v1] Fri, 10 Apr 2026 08:19:48 UTC (671 KB) Access Paper: HTML (experimental) view license Current browse context: cs.SE < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.AI cs.CR References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)