← Back ◬ AI & Machine Learning Apr 22, 2026

SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection

arXiv Security Archived Apr 22, 2026 ✓ Full text saved

arXiv:2604.19031v1 Announce Type: new Abstract: Software vulnerabilities are a primary threat to modern infrastructure. While static analysis and Graph Neural Networks have long served as the foundation for vulnerability detection, the emergence of Large Language Models (LLMs) has introduced a transformative paradigm driven by superior semantic reasoning and cross-environment generalization. However, in the context of LLM-based vulnerability detection, we identify a fundamental bottleneck in the

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Cryptography and Security [Submitted on 21 Apr 2026] SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection Zhengyang Shan, Xu Qian, Jiayun Xin, Minghui Xu, Yue Zhang, Zhen Yang, Hao Wu, Xiuzhen Cheng Software vulnerabilities are a primary threat to modern infrastructure. While static analysis and Graph Neural Networks have long served as the foundation for vulnerability detection, the emergence of Large Language Models (LLMs) has introduced a transformative paradigm driven by superior semantic reasoning and cross-environment generalization. However, in the context of LLM-based vulnerability detection, we identify a fundamental bottleneck in these models termed \textbf{Signal Submersion}: a state where features related to vulnerability are activated internally but numerically overwhelmed by dominant functional semantics. To address this, we propose \textbf{SAGE} (\textbf{S}ignal-\textbf{A}mplified \textbf{G}uided \textbf{E}mbeddings), a framework that shifts from passive signal submersion to active signal recovery. SAGE integrates task-conditional Sparse Autoencoders (SAEs) to isolate and amplify these faint vulnerability signals. Extensive evaluations on BigVul, PrimeVul, and PreciseBugs demonstrate that SAGE achieves state-of-the-art performance. Notably, SAGE mitigates Signal Submersion by increasing the internal Signal-to-Noise Ratio (SNR) by 12.7\times via sparse manifold projection. This mechanistic intervention enables a 7B model to achieve up to 318\% Matthews Correlation Coefficient (MCC) gains on unseen distributions and a 319\% gain on classic datasets. By maintaining robust performance across 13 programming languages and outperforming 34B baselines, SAGE establishes a more efficient and scalable path to software security than simple parameter scaling. Comments: 24 pages, 6 figures, 6 tables. Accepted by ISSTA 2026 Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2604.19031 [cs.CR] (or arXiv:2604.19031v1 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2604.19031 Focus to learn more Submission history From: Minghui Xu [view email] [v1] Tue, 21 Apr 2026 03:27:59 UTC (3,106 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev | next > new | recent | 2026-04 Change to browse by: cs 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?)

💬 Team Notes