论文标题
使用2D全息降低表示，在不信任的平台上部署卷积网络
Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations
论文作者
论文摘要
由于对神经网络的运行推断的计算成本，因此通常需要在第三方的计算环境或硬件上部署推论步骤。如果第三方不完全信任，则需要混淆输入和输出的性质，以便第三方无法轻易确定执行哪些特定任务。事实证明，存在利用不受信任的政党的协议，但在实践中运行的计算要求太高了。相反，我们探索了一种称为Connectionist象征性伪秘密的快速启发式安全策略。通过利用全息图减少表示（HRR），我们创建了一个具有伪加密风格的防御的神经网络，从经验上表现出稳健性的攻击性，即使在不切实际地支持对手的威胁模型下也是如此。
Due to the computational cost of running inference for a neural network, the need to deploy the inferential steps on a third party's compute environment or hardware is common. If the third party is not fully trusted, it is desirable to obfuscate the nature of the inputs and outputs, so that the third party can not easily determine what specific task is being performed. Provably secure protocols for leveraging an untrusted party exist but are too computational demanding to run in practice. We instead explore a different strategy of fast, heuristic security that we call Connectionist Symbolic Pseudo Secrets. By leveraging Holographic Reduced Representations (HRR), we create a neural network with a pseudo-encryption style defense that empirically shows robustness to attack, even under threat models that unrealistically favor the adversary.
