@inproceedings{huang-etal-2026-deepguard,
    title = "{D}eep{G}uard: Secure Code Generation via Multi-Layer Semantic Aggregation",
    author = "Huang, Li  and
      Liu, Zhongxin  and
      Wu, Yifan  and
      Yin, Tao  and
      li, Dong  and
      Bi, Jichao  and
      Mu, Nankun  and
      Zhang, Hongyu  and
      Yan, Meng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.907/",
    pages = "19793--19813",
    ISBN = "979-8-89176-390-6",
    abstract = "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."
}