ID	原文	译文
3423	所提方案结合分布式密钥生成技术实现用户属性私钥的(t,n)门限生成机制，可以抵抗最多来自 t−1 个授权中心的合谋攻击。	Distributed key generation technology was integrated to realize the(t,n) threshold generation mechanism of the user's private key, which could resist collusion attacks from at most t−1 au-thorities.
3424	利用双线性映射构造了所提方案，分析了所提方案的安全性、计算开销和通信开销，并与同类型方案做比较。	Utilizing bilinear mapping, a specific multi-authority attribute-based identification scheme was constructed. The security, computation cost and communication cost of the proposed scheme was analyzed, and it was compared with thesame type of schemes.
3425	最后，以多因子身份认证为例，分析了所提方案在电子凭据应用场景中的可行性。分析结果表明，所提方案具有更优的综合性能。	Finally, taking multi-factor identification as an example, the feasibility of the proposed scheme inthe application scenario of electronic credentials was analyzed.The result shows that the proposed scheme has bettercomprehensive performance.
3426	针对图像采集和传输过程中所产生噪声导致后续图像处理能力下降的问题，提出基于生成对抗网络（GAN）的多通道图像去噪算法。	Aiming at the issue that the noise generated during image acquisition and transmission would degrade the abil-ity of subsequent image processing, a generative adversarial network (GAN) based multi-channel image denoising algo-rithm was developed.
3427	所提算法将含噪彩色图像分离为 RGB 三通道，各通道基于具有相同架构的端到端可训练的 GAN 实现去噪。	The noisy color image could be separated into red-green-blue (RGB) three channels via the pro-posed approach, and then the denoising could be implemented in each channel on the basis of an end-to-end trainableGAN with the same architecture.
3428	GAN 生成网络基于 U-net 衍生网络以及残差块构建，从而可参考低级特征信息以有效提取深度特征进而避免丢失细节信息；	The generator module of GAN was constructed based on the U-net derivative networkand residual blocks such that the high-level feature information could be extracted effectively via referring to thelow-level feature information to avoid the loss of the detail information.
3429	判别网络则基于全卷积网络构造，因而可获得像素级分类从而提升判别精确性。	In the meantime, the discriminator module couldbe demonstrated on the basis of fully convolutional neural network such that the pixel-level classification could be achieved to improve the discrimination accuracy.
3430	此外，为改善去噪能力且尽可能保留图像细节信息，所构建去噪网络基于对抗损失、视觉感知损失和均方误差损失这 3 类损失度量构建复合损失函数。	Besides, in order to improve the denoising ability and retain the imagedetail as much as possible, the composite loss function could be depicted by the illustrated denoising network based onthe following three loss measures, adversarial loss, visual perception loss, and mean square error (MSE).
3431	最后，利用算术平均方法融合三通道输出信息以获得最终去噪图像。	Finally, the re-sultant three-channel output information could be fused by exploiting the arithmetic mean method to obtain the final de-noised image.
3432	实验结果表明，与主流算法相比，所提算法可有效去除图像噪声，且可较好地恢复原始图像细节。	Compared with the state-of-the-art algorithms, experimental results show that the proposed algorithm canremove the image noise effectively and restore the original image details considerably.