在这项工作中，我们提出了清洁nunet，这是原始波形上的因果语音deno的模型。所提出的模型基于编码器架构，并结合了几个自我注意块，以完善其瓶颈表示，这对于获得良好的结果至关重要。该模型通过在波形和多分辨率光谱图上定义的一组损失进行了优化。所提出的方法在各种客观和主观评估指标中的言语质量方面优于最先进的模型。

In this work, we devise robust and efficient learning protocols for orchestrating a Federated Learning (FL) process for the Federated Tumor Segmentation Challenge (FeTS 2022). Enabling FL for FeTS setup is challenging mainly due to data heterogeneity among collaborators and communication cost of training. To tackle these challenges, we propose Robust Learning Protocol (RoLePRO) which is a combination of server-side adaptive optimisation (e.g., server-side Adam) and judicious parameter (weights) aggregation schemes (e.g., adaptive weighted aggregation). RoLePRO takes a two-phase approach, where the first phase consists of vanilla Federated Averaging, while the second phase consists of a judicious aggregation scheme that uses a sophisticated reweighting, all in the presence of an adaptive optimisation algorithm at the server. We draw insights from extensive experimentation to tune learning rates for the two phases.

由于隐私立法赋予用户有权被遗忘的权利，因此使模型忘记其某些培训数据已经成为必不可少的。我们探讨了删除任何客户在联邦学习（FL）中的贡献的问题。在FL回合中，每个客户都进行本地培训，以学习一个模型，以最大程度地减少其私人数据的经验损失。我们建议通过逆转学习过程，即训练模型\ emph {最大化}局部经验损失来对客户（将要删除）进行学习。 In particular, we formulate the unlearning problem as a constrained maximization problem by restricting to an $\ell_2$-norm ball around a suitably chosen reference model to help retain some knowledge learnt from the other clients' data.这使客户可以使用投影的梯度下降来执行学习。该方法确实不需要全局访问用于培训的数据，也不需要由聚合器（服务器）或任何客户端存​​储的参数更新历史记录。 MNIST数据集的实验表明，所提出的未学习方法是有效的。

Machine Unering是指删除培训数据子集的任务，从而删除其对训练有素的模型的贡献。近似学习是该任务的一类方法，避免了需要在保留数据上从头开始重新研究模型。贝叶斯的规则可用于将近似学习作为推理问题，其中目的是通过划分删除数据的可能性来获得更新后的后部。但是，这有自己的挑战集，因为人们通常无法访问模型参数的确切后验。在这项工作中，我们检查了拉普拉斯近似和变异推理的使用以获得更新的后验。通过对指导示例进行回归任务的神经网络培训，我们在实践场景中就贝叶斯学习的适用性进行了见解。

在联合学习（FL）中，已经开发出强大的聚合方案来防止恶意客户。许多强大的聚合方案依赖于某些数量的良性客户端存在于工人的仲裁中。当客户端可以加入WILL或基于空闲系统状态等因素时，这可能很难保证，并连接到电源和WiFi。我们解决在犯罪者可能完全恶意时，解决对抗对抗训练的保护的场景。我们模拟了一种攻击者，攻击模型将弱点插入对抗培训，使得该模型显示出明显的对抗性鲁棒性，而攻击者可以利用插入的弱点来绕过对抗性训练并强迫模型错误分类对抗性示例。我们使用抽象的解释技术来检测此类隐秘攻击并阻止损坏的模型更新。我们表明，即使对适应性攻击者，这种防御也可以保持对抗性鲁棒性。

Deep Generative Models (DGMs) are a popular class of deep learning models which find widespread use because of their ability to synthesize data from complex, high-dimensional manifolds. However, even with their increasing industrial adoption, they haven't been subject to rigorous security and privacy analysis. In this work we examine one such aspect, namely backdoor attacks on DGMs which can significantly limit the applicability of pre-trained models within a model supply chain and at the very least cause massive reputation damage for companies outsourcing DGMs form third parties. While similar attacks scenarios have been studied in the context of classical prediction models, their manifestation in DGMs hasn't received the same attention. To this end we propose novel training-time attacks which result in corrupted DGMs that synthesize regular data under normal operations and designated target outputs for inputs sampled from a trigger distribution. These attacks are based on an adversarial loss function that combines the dual objectives of attack stealth and fidelity. We systematically analyze these attacks, and show their effectiveness for a variety of approaches like Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as well as different data domains including images and audio. Our experiments show that - even for large-scale industry-grade DGMs (like StyleGAN) - our attacks can be mounted with only modest computational effort. We also motivate suitable defenses based on static/dynamic model and output inspections, demonstrate their usefulness, and prescribe a practical and comprehensive defense strategy that paves the way for safe usage of DGMs.

Recent work has made significant progress in improving spatial resolution for pixelwise labeling with Fully Convolutional Network (FCN) framework by employing Dilated/Atrous convolution, utilizing multi-scale features and refining boundaries. In this paper, we explore the impact of global contextual information in semantic segmentation by introducing the Context Encoding Module, which captures the semantic context of scenes and selectively highlights class-dependent featuremaps. The proposed Context Encoding Module significantly improves semantic segmentation results with only marginal extra computation cost over FCN. Our approach has achieved new state-of-theart results 51.7% mIoU on PASCAL-Context, 85.9% mIoU on PASCAL VOC 2012. Our single model achieves a final score of 0.5567 on ADE20K test set, which surpasses the winning entry of COCO-Place Challenge 2017. In addition, we also explore how the Context Encoding Module can improve the feature representation of relatively shallow networks for the image classification on CIFAR-10 dataset. Our 14 layer network has achieved an error rate of 3.45%, which is comparable with state-of-the-art approaches with over 10× more layers. The source code for the complete system are publicly available 1 .