How Vulnerable Are Edge LLMs?

Computer Science > Cryptography and Security [Submitted on 25 Mar 2026] How Vulnerable Are Edge LLMs? Ao Ding, Hongzong Li, Zi Liang, Zhanpeng Shi, Shuxin Zhuang, Shiqin Tang, Rong Feng, Ping Lu Large language models (LLMs) are increasingly deployed on edge devices under strict computation and quantization constraints, yet their security implications remain unclear. We study query-based knowledge extraction from quantized edge-deployed LLMs under realistic query budgets and show that, although quantization introduces noise, it does not remove the underlying semantic knowledge, allowing substantial behavioral recovery through carefully designed queries. To systematically analyze this risk, we propose \textbf{CLIQ} (\textbf{Cl}ustered \textbf{I}nstruction \textbf{Q}uerying), a structured query construction framework that improves semantic coverage while reducing redundancy. Experiments on quantized Qwen models (INT8/INT4) demonstrate that CLIQ consistently outperforms original queries across BERTScore, BLEU, and ROUGE, enabling more efficient extraction under limited budgets. These results indicate that quantization alone does not provide effective protection against query-based extraction, highlighting a previously underexplored security risk in edge-deployed LLMs. Subjects: Cryptography and Security (cs.CR); Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2603.23822 [cs.CR]   (or arXiv:2603.23822v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2603.23822 Focus to learn more Submission history From: Hongzong Li [view email] [v1] Wed, 25 Mar 2026 01:10:38 UTC (4,862 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.CL cs.LG 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?)