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.

翻译：深度神经网络（DNNs）具有高价值知识产权（IP），然而将其部署到边缘环境会使其面临**无限制的甲骨文访问**，从而易受模型提取和逆向攻击。现有防御措施在实际应用中难以奏效：被动水印仅提供事后溯源能力，而主动防御则会引入过高的延迟或需要持续访问敏感训练数据。为弥补这一缺陷，我们提出**LymphNode**——一种新型事后防御框架，它作为模型内部的固有“免疫系统”发挥作用。LymphNode实施严格的“默认拒绝”策略：通过向特征空间注入**广义稀疏通用对抗扰动（GSUAP）**，主动中和未授权查询的模型效用，有效阻断梯度估计与数据推断。仅对携带隐蔽特征域凭证的授权输入选择性恢复模型效用。本框架具有高度实用性：**数据高效**，使用不到100个样本（<1%训练数据）即可建立稳健防护；**跨数据集适应**，可利用公开替代数据集实现保护。因此，LymphNode为原始训练数据受限或不可用的高风险场景提供了一种轻量级、可即刻部署的防御方案。