In terms of artificial intelligence, there are several security and privacy deficiencies in the traditional centralized training methods of machine learning models by a server. To address this limitation, federated learning (FL) has been proposed and is known for breaking down ``data silos" and protecting the privacy of users. However, FL has not yet gained popularity in the industry, mainly due to its security, privacy, and high cost of communication. For the purpose of advancing the research in this field, building a robust FL system, and realizing the wide application of FL, this paper sorts out the possible attacks and corresponding defenses of the current FL system systematically. Firstly, this paper briefly introduces the basic workflow of FL and related knowledge of attacks and defenses. It reviews a great deal of research about privacy theft and malicious attacks that have been studied in recent years. Most importantly, in view of the current three classification criteria, namely the three stages of machine learning, the three different roles in federated learning, and the CIA (Confidentiality, Integrity, and Availability) guidelines on privacy protection, we divide attack approaches into two categories according to the training stage and the prediction stage in machine learning. Furthermore, we also identify the CIA property violated for each attack method and potential attack role. Various defense mechanisms are then analyzed separately from the level of privacy and security. Finally, we summarize the possible challenges in the application of FL from the aspect of attacks and defenses and discuss the future development direction of FL systems. In this way, the designed FL system has the ability to resist different attacks and is more secure and stable.

Human reading comprehension often requires reasoning of event semantic relations in narratives, represented by Event-centric Question-Answering (QA). To address event-centric QA, we propose a novel QA model with contrastive learning and invertible event transformation, call TranCLR. Our proposed model utilizes an invertible transformation matrix to project semantic vectors of events into a common event embedding space, trained with contrastive learning, and thus naturally inject event semantic knowledge into mainstream QA pipelines. The transformation matrix is fine-tuned with the annotated event relation types between events that occurred in questions and those in answers, using event-aware question vectors. Experimental results on the Event Semantic Relation Reasoning (ESTER) dataset show significant improvements in both generative and extractive settings compared to the existing strong baselines, achieving over 8.4% gain in the token-level F1 score and 3.0% gain in Exact Match (EM) score under the multi-answer setting. Qualitative analysis reveals the high quality of the generated answers by TranCLR, demonstrating the feasibility of injecting event knowledge into QA model learning. Our code and models can be found at https://github.com/LuJunru/TranCLR.

在基于变压器的模型中通常观察到令牌均匀性，在经过变压器中经过堆叠的多个自我发场层后，不同的令牌共享大量相似信息。在本文中，我们建议使用每个变压器层的输出的奇异值的分布来表征令牌均匀性的现象，并从经验上说明，偏斜的奇异值分布可以减轻“令牌均匀性”问题。基于我们的观察结果，我们定义了奇异值分布的几种理想特性，并提出了一种新的转换函数，以更新奇异值。我们表明，除了减轻令牌均匀性外，转换功能还应保留原始嵌入空间中的当地邻域结构。我们提出的奇异价值变换函数应用于伯特，阿尔伯特，罗伯塔和德文尔特等一系列基于变压器的语言模型，并且在语义文本相似性评估和一系列胶水任务中观察到了改善的性能。我们的源代码可在https://github.com/hanqi-qi/tokenuni.git上找到。

特定的发射极识别（SEI）是物理层身份验证的高潜在技术，它是上层身份验证的最关键补充之一。 SEI基于电路差而不是密码学的射频（RF）特征。这些功能是硬件电路的固有特征，很难伪造。最近，已经提出了各种基于深度学习（DL）的常规SEI方法，并实现了高级性能。但是，提出了这些方法，用于使用大量的RF信号样品进行训练的近距离场景，并且在训练样品有限的情况下，它们的性能较差。因此，我们将重点放在几个射击SEI（FS-SEI）上，用于通过自动依赖的监视播（ADS-B）信号进行飞机识别，并根据深度度量集合学习（DMEL）提出了一种新颖的FS-SEI方法。具体而言，提出的方法包括特征嵌入和分类。前者基于具有复杂价值的卷积神经网络（CVCNN）的度量学习，用于提取具有紧凑的类别内距离和可分离类别间距离的区分特征，而后者则由集合分类器实现。仿真结果表明，如果每个类别的样本数量超过5，则我们提出的方法的平均准确性高于98 \％。此外，特征可视化证明了我们提出的方法在可区分性和概括方面的优势。本文的代码可以从GitHub（https://github.com/beechburgpiestar/few-shot-specific-emitter-emitter-istifification-via-deep-metric-metric-semble-learning）下载。

在保持最佳控制性能的同时，减少传感器要求对于许多工业控制应用至关重要，以实现强大的，低成本和计算有效的控制器。但是，对于典型的机器学习域的现有特征选择解决方案几乎不可能通过变化的动态来控制在控制域中。在本文中，一个新颖的框架，即双世界嵌入式细心特征选择（D-AFS），可以有效地为动态控制下的系统选择最相关的传感器。 D-AFS并没有在大多数深度强化学习（DRL）算法中使用的一个世界，而是具有扭曲功能的现实世界和虚拟同行。通过分析在两个世界中DRL的响应，D-AFS可以定量确定各自特征对控制的重要性。众所周知的主动流控制问题，圆柱阻力减少，用于评估。结果表明，D-AFS成功地发现了比最先进的解决方案，比人类专家的五探针布局比最先进的解决方案进行了18.7 \％阻力的优化五探针布局。我们还将该解决方案应用于四个OpenAI经典控制案例。在所有情况下，D-AFS都比最初提供的解决方案获得相同或更好的传感器配置。我们认为，结果突出显示了为实验或工业系统实现高效和最佳传感器设计的一种新方法。我们的源代码可在https://github.com/g-yab/dafsfluid上公开提供。

近年来，人们对开发自然语言处理（NLP）中可解释模型的利益越来越多。大多数现有模型旨在识别输入功能，例如对于模型预测而言重要的单词或短语。然而，在NLP中开发的神经模型通常以层次结构的方式构成单词语义，文本分类需要层次建模来汇总本地信息，以便处理主题和标签更有效地转移。因此，单词或短语的解释不能忠实地解释文本分类中的模型决策。本文提出了一种新型的层次解释性神经文本分类器，称为提示，该分类器可以自动以层次结构方式以标记相关主题的形式生成模型预测的解释。模型解释不再处于单词级别，而是基于主题作为基本语义单元。评论数据集和新闻数据集的实验结果表明，我们所提出的方法与现有最新的文本分类器相当地达到文本分类结果，并比其他可解释的神经文本更忠实于模型的预测和更好地理解人类的解释分类器。

我们研究了在联合环境中从积极和未标记的（PU）数据中学习的问题，由于资源和时间的限制，每个客户仅标记其数据集的一小部分。与传统的PU学习中的设置不同，负面类是由单个类组成的，而由客户在联合设置中无法识别的否定样本可能来自客户未知的多个类。因此，在这种情况下，几乎无法应用现有的PU学习方法。为了解决这个问题，我们提出了一个新颖的框架，即使用正面和未标记的数据（FEDPU）联合学习，以通过利用其他客户的标记数据来最大程度地降低多个负面类别的预期风险。我们理论上分析了拟议的FedPU的概括结合。经验实验表明，FedPU比常规监督和半监督联盟的学习方法取得更好的性能。

Human pose estimation has been widely applied in various industries. While recent decades have witnessed the introduction of many advanced two-dimensional (2D) human pose estimation solutions, three-dimensional (3D) human pose estimation is still an active research field in computer vision. Generally speaking, 3D human pose estimation methods can be divided into two categories: single-stage and two-stage. In this paper, we focused on the 2D-to-3D lifting process in the two-stage methods and proposed a more advanced baseline model for 3D human pose estimation, based on the existing solutions. Our improvements include optimization of machine learning models and multiple parameters, as well as introduction of a weighted loss to the training model. Finally, we used the Human3.6M benchmark to test the final performance and it did produce satisfactory results.

Multilingual BERT (mBERT) has demonstrated considerable cross-lingual syntactic ability, whereby it enables effective zero-shot cross-lingual transfer of syntactic knowledge. The transfer is more successful between some languages, but it is not well understood what leads to this variation and whether it fairly reflects difference between languages. In this work, we investigate the distributions of grammatical relations induced from mBERT in the context of 24 typologically different languages. We demonstrate that the distance between the distributions of different languages is highly consistent with the syntactic difference in terms of linguistic formalisms. Such difference learnt via self-supervision plays a crucial role in the zero-shot transfer performance and can be predicted by variation in morphosyntactic properties between languages. These results suggest that mBERT properly encodes languages in a way consistent with linguistic diversity and provide insights into the mechanism of cross-lingual transfer.

In this work, we present a novel framework built to simplify 3D asset generation for amateur users. To enable interactive generation, our method supports a variety of input modalities that can be easily provided by a human, including images, text, partially observed shapes and combinations of these, further allowing to adjust the strength of each input. At the core of our approach is an encoder-decoder, compressing 3D shapes into a compact latent representation, upon which a diffusion model is learned. To enable a variety of multi-modal inputs, we employ task-specific encoders with dropout followed by a cross-attention mechanism. Due to its flexibility, our model naturally supports a variety of tasks, outperforming prior works on shape completion, image-based 3D reconstruction, and text-to-3D. Most interestingly, our model can combine all these tasks into one swiss-army-knife tool, enabling the user to perform shape generation using incomplete shapes, images, and textual descriptions at the same time, providing the relative weights for each input and facilitating interactivity. Despite our approach being shape-only, we further show an efficient method to texture the generated shape using large-scale text-to-image models.