XNN：云使能深度学习中缓解身份泄漏的范式转变
XNN: Paradigm Shift in Mitigating Identity Leakage within Cloud-Enabled Deep Learning
AI总结：
本文提出 XNN 和 XNN-d 两种方法，通过随机置换与矩阵乘法混淆训练特征、利用对抗训练噪声保护推理特征，在云深度学习中人脸识别场景下显著降低身份泄漏并保持高准确率。
摘要：
在基于云的深度学习领域，对外部计算资源的需求与严峻的隐私问题并存，尤其是身份泄漏问题。为应对这一挑战，我们提出了 XNN 和 XNN-d，这两种开创性方法将随机扰动注入神经网络特征，在效用与隐私之间取得了和谐的平衡。XNN 面向训练阶段设计，巧妙地将随机置换与矩阵乘法技术相结合来混淆特征图，在不损害训练完整性的前提下有效保护私有数据免受潜在泄露。同时，XNN-d 面向推理阶段设计，采用对抗训练来整合生成对抗噪声。该技术有效抵御旨在提取身份的黑盒访问攻击，而一个蒸馏人脸识别网络则能熟练处理扰动后的特征，确保准确识别。我们的评估证明了 XNN 的有效性，在显著减少身份泄漏的同时保持了较高的模型准确率，明显优于现有方法。
英文摘要：
In the domain of cloud-based deep learning, the imperative for external computational resources coexists with acute privacy concerns, particularly identity leakage. To address this challenge, we introduce XNN and XNN-d, pioneering methodologies that infuse neural network features with randomized perturbations, striking a harmonious balance between utility and privacy. XNN, designed for the training phase, ingeniously blends random permutation with matrix multiplication techniques to obfuscate feature maps, effectively shielding private data from potential breaches without compromising training integrity. Concurrently, XNN-d, devised for the inference phase, employs adversarial training to integrate generative adversarial noise. This technique effectively counters black-box access attacks aimed at identity extraction, while a distilled face recognition network adeptly processes the perturbed features, ensuring accurate identification. Our evaluation demonstrates XNN's effectiveness, significantly outperforming existing methods in reducing identity leakage while maintaining a high model accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
