LymphNode: A Plug-and-Play Access Control Method for Deep Neural Networks

Computer Science > Cryptography and Security [Submitted on 15 May 2026] LymphNode: A Plug-and-Play Access Control Method for Deep Neural Networks Hanyu Pei, Shang Liu, Zeyan Liu Deep Neural Networks (DNNs) are high-value intellectual property (IP), yet deploying them to edge environments exposes them to \textbf{unrestricted oracle access}, rendering them vulnerable to model extraction and inversion attacks. Existing defenses fail to address this practically: passive watermarking only offers post-hoc provenance, while active defenses impose prohibitive latency or require persistent access to sensitive training data. To bridge this gap, we propose \textit{LymphNode}, a novel post-hoc defense framework that acts as an intrinsic ``immune system" within the model. \textit{LymphNode} enforces a strict ``default-deny'' policy: it actively neutralizes model utility for unauthorized queries via \textbf{Generalized Sparse Universal Adversarial Perturbations (GSUAP)} injected into the feature space, effectively blocking gradient estimation and data inference. Utility is selectively restored only for authorized inputs carrying a stealthy feature-domain credential. Our framework is highly practical: it is \textbf{data-efficient}, establishing robust protection with fewer than 100 samples (<1\% of training data), and \textbf{cross-dataset adaptable}, enabling protection using public surrogate datasets. \textit{LymphNode} thus provides a lightweight, immediately deployable defense for high-stakes scenarios where original training data is restricted or unavailable. Comments: Accepted by the 56th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN 2026). Author accepted manuscript. 14 pages, 6 figures Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2605.16227 [cs.CR]   (or arXiv:2605.16227v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.16227 Focus to learn more Submission history From: Hanyu Pei [view email] [v1] Fri, 15 May 2026 17:38:06 UTC (572 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 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?)