CTX-Coder: Cross-Attention Architectures Empower LLMs for Long-Context Vulnerability Detection

Jujie Wang; Kangfeng Zheng; Bin Wu; Chunhua Wu; Yulin Yao; Jiaqi Gao; Minjiao Yang

AAAI 2026technical0 citations

CTX-Coder: Cross-Attention Architectures Empower LLMs for Long-Context Vulnerability Detection

Jujie Wang, Kangfeng Zheng, Bin Wu, Chunhua Wu, Yulin Yao, Jiaqi Gao, Minjiao Yang

Abstract

Software vulnerabilities have increased sharply, underscoring the growing urgency for effective detection methods. Although large language model (LLM) based methods have shown promise in this task, current state-of-the-art LLM approaches struggle with functions that have long contexts. In this paper, we propose CTX-Coder, a context-enhanced vulnerability detection framework that enables LLMs to selectively focus on relevant contextual functions. To achieve this, we represent the contextual functions as embeddings and integrate them with the target code via cross-attention, thereby enhancing the model

BibTeX

@inproceedings{aaai2026_ctxcodercrossatt,
  title = {CTX-Coder: Cross-Attention Architectures Empower LLMs for Long-Context Vulnerability Detection},
  author = {Jujie Wang and Kangfeng Zheng and Bin Wu and Chunhua Wu and Yulin Yao and Jiaqi Gao and Minjiao Yang},
  booktitle = {AAAI 2026},
  year = {2026}
}