Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While various point cloud completion models have demonstrated their powerful capabilities, their robustness against adversarial attacks, which have been proven to be fatally malicious towards deep neural networks, remains unknown. In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes. In order to evaluate the robustness of the completion models, we propose PointCA, the first adversarial attack against 3D point cloud completion models. PointCA can generate adversarial point clouds that maintain high similarity with the original ones, while being completed as another object with totally different semantic information. Specifically, we minimize the representation discrepancy between the adversarial example and the target point set to jointly explore the adversarial point clouds in the geometry space and the feature space. Furthermore, to launch a stealthier attack, we innovatively employ the neighbourhood density information to tailor the perturbation constraint, leading to geometry-aware and distribution-adaptive modifications for each point. Extensive experiments against different premier point cloud completion networks show that PointCA can cause a performance degradation from 77.9% to 16.7%, with the structure chamfer distance kept below 0.01. We conclude that existing completion models are severely vulnerable to adversarial examples, and state-of-the-art defenses for point cloud classification will be partially invalid when applied to incomplete and uneven point cloud data.
translated by 谷歌翻译
人群计数是一项回归任务,它估计场景图像中的人数,在一系列安全至关重要的应用程序中起着至关重要的作用,例如视频监视,交通监控和流量控制。在本文中,我们研究了基于深度学习的人群计数模型对后门攻击的脆弱性,这是对深度学习的主要安全威胁。后门攻击者通过数据中毒将后门触发植入目标模型,以控制测试时间的预测。与已经开发和测试的大多数现有后门攻击的图像分类模型不同,人群计数模型是输出多维密度图的回归模型,因此需要不同的技术来操纵。在本文中,我们提出了两次新颖的密度操纵后门攻击(DMBA $^{ - } $和DMBA $^{+} $),以攻击模型以产生任意的大或小密度估计。实验结果证明了我们对五个经典人群计数模型和四种类型数据集的DMBA攻击的有效性。我们还深入分析了后门人群计数模型的独特挑战,并揭示了有效攻击的两个关键要素:1)完整而密集的触发器以及2)操纵地面真相计数或密度图。我们的工作可以帮助评估人群计数模型对潜在后门攻击的脆弱性。
translated by 谷歌翻译
图形离群值检测是一项具有许多应用程序的新兴但至关重要的机器学习任务。尽管近年来算法扩散,但缺乏标准和统一的绩效评估设置限制了它们在现实世界应用中的进步和使用。为了利用差距,我们(据我们所知)(据我们所知)第一个全面的无监督节点离群值检测基准为unod,并带有以下亮点:(1)评估骨架从经典矩阵分解到最新图形神经的骨架的14个方法网络; (2)在现实世界数据集上使用不同类型的注射异常值和自然异常值对方法性能进行基准测试; (3)通过在不同尺度的合成图上使用运行时和GPU存储器使用算法的效率和可扩展性。基于广泛的实验结果的分析,我们讨论了当前渠道方法的利弊,并指出了多个关键和有希望的未来研究方向。
translated by 谷歌翻译
我们考虑了一个联合表示的学习框架,在中央服务器的协助下,一组$ n $分布式客户通过其私人数据协作培训一组实体的表示(或嵌入)(例如,用户在一个中的用户社交网络)。在此框架下,对于以私人方式汇总在客户培训的本地嵌入的关键步骤,我们开发了一个名为SECEA的安全嵌入聚合协议,该协议为一组实体提供信息理论隐私保证,并在每个客户端提供相应的嵌入$同时$ $,对好奇的服务器和最多$ t <n/2 $勾结的客户。作为SECEA的第一步,联合学习系统执行了一个私人实体联盟,让每个客户在不知道哪个实体属于哪个客户的情况下学习系统中的所有实体。在每个聚合回合中,使用Lagrange插值在客户端中秘密共享本地嵌入,然后每个客户端构造编码的查询以检索预期实体的聚合嵌入。我们对各种表示的学习任务进行全面的实验,以评估SECEA的效用和效率,并从经验上证明,与没有(或具有较弱的)隐私保证的嵌入聚合协议相比,SECEA会造成可忽略的绩效损失(5%以内); SECEA的附加计算潜伏期减小,用于培训较大数据集的更深层次模型。
translated by 谷歌翻译
复杂知识库问题回答是过去十年的一个流行的研究领域。最近的公共数据集导致这一领域的令人鼓舞的结果,但主要涉及英语,只涉及少数问题类型和关系,在更现实的环境和英语以外的语言中妨碍研究。此外,很少有最先进的KBQA模型在Wikidata上培训,是最受欢迎的真实知识库之一。我们提出了CLC-Quad,这是Wikidata的第一个大规模复杂的中文语义解析数据集,以解决这些挑战。我们与数据集一起介绍了一个文本到SPARQL基线模型,可以有效地应答多种类型的复杂问题,例如事实上的问题,双重意图问题,布尔问题和计数问题,以及Wikidata作为背景知识。我们终于分析了SOTA KBQA模型在此数据集中的表现,并确定了中国KBQA面临的挑战。
translated by 谷歌翻译
语义变化检测(SCD)扩展了多级变化检测(MCD)任务,不仅提供了更改位置,而且提供了观察间隔之前和之后的详细覆盖/土地使用(LCLU)类别。这种细粒度的语义变更信息在许多应用中非常有用。最近的研究表明,SCD可以通过三分支卷积神经网络(CNN)进行建模,其包含两个时间分支和变化分支。然而,在这种架构中,时间分支和改变分支之间的通信不足。为了克服现有方法中的限制,我们提出了一种用于SCD的新型CNN架构,其中语义时间特征在深CD单元中合并。此外,我们详细说明了这种架构,以推理双颞态语义相关性。由此产生的双时话语义推理网络(BI-SRNET)包含两种类型的语义推理块,以推理单时段和跨时话语义相关性,以及提高改变变化检测结果的语义一致性的新型损失功能。基准数据集上的实验结果表明,该架构对现有方法获得了显着的准确性改进,而Bi-SRNET中的添加设计则进一步提高了语义类别和改变区域的分割。本文的代码可访问:github.com/gnsding/bi-srnet。
translated by 谷歌翻译
由于其独特的现实世界对象及其互动,图表已广泛用于数据挖掘和机器学习。如图所说,如图所说,通常会看到它们的子图分别收集并存储在多个本地系统中。因此,考虑子图联合学习设置是自然的,其中每个本地系统保持一个可以从整个图的分布偏置的小子图。因此,子图联合的学习旨在协同培训强大且更广泛的图形挖掘模型,而无需直接共享其图形数据。在这项工作中,朝着小型但是逼真的子图联合学习设置,我们提出了两种主要技术:(1)联邦品,其基于FedAVG的基于FaItaVG列出的GraphSage模型,以在多个本地子图上集成节点特征,链接结构和任务标签; (2)FEDSAGE +,它沿edsage举办丢失的邻居生成器,以处理跨本地子图的缺失链接。具有合成子图联合学习设置的四个真实图形数据集的经验结果证明了我们所提出的技术的有效性和效率。同时,一致的理论意义是以全局图对的泛化能力。
translated by 谷歌翻译
机器学习(ML)模型已广泛应用于各种应用,包括图像分类,文本生成,音频识别和图形数据分析。然而,最近的研究表明,ML模型容易受到隶属推导攻击(MIS),其目的是推断数据记录是否用于训练目标模型。 ML模型上的MIA可以直接导致隐私违规行为。例如,通过确定已经用于训练与某种疾病相关的模型的临床记录,攻击者可以推断临床记录的所有者具有很大的机会。近年来,MIS已被证明对各种ML模型有效,例如,分类模型和生成模型。同时,已经提出了许多防御方法来减轻米西亚。虽然ML模型上的MIAS形成了一个新的新兴和快速增长的研究区,但还没有对这一主题进行系统的调查。在本文中,我们对会员推论和防御进行了第一个全面调查。我们根据其特征提供攻击和防御的分类管理,并讨论其优点和缺点。根据本次调查中确定的限制和差距,我们指出了几个未来的未来研究方向,以激发希望遵循该地区的研究人员。这项调查不仅是研究社区的参考,而且还为该研究领域之外的研究人员带来了清晰的照片。为了进一步促进研究人员,我们创建了一个在线资源存储库,并与未来的相关作品继续更新。感兴趣的读者可以在https://github.com/hongshenghu/membership-inference-machine-learning-literature找到存储库。
translated by 谷歌翻译
Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multi-modal interactions with query sentence for reasoning. However, we argue that these methods have overlooked two indispensable issues: 1) Boundary-bias: The annotated target segment generally refers to two specific frames as corresponding start and end timestamps. The video downsampling process may lose these two frames and take the adjacent irrelevant frames as new boundaries. 2) Reasoning-bias: Such incorrect new boundary frames also lead to the reasoning bias during frame-query interaction, reducing the generalization ability of model. To alleviate above limitations, in this paper, we propose a novel Siamese Sampling and Reasoning Network (SSRN) for TSG, which introduces a siamese sampling mechanism to generate additional contextual frames to enrich and refine the new boundaries. Specifically, a reasoning strategy is developed to learn the inter-relationship among these frames and generate soft labels on boundaries for more accurate frame-query reasoning. Such mechanism is also able to supplement the absent consecutive visual semantics to the sampled sparse frames for fine-grained activity understanding. Extensive experiments demonstrate the effectiveness of SSRN on three challenging datasets.
translated by 谷歌翻译
Data heterogeneity across clients in federated learning (FL) settings is a widely acknowledged challenge. In response, personalized federated learning (PFL) emerged as a framework to curate local models for clients' tasks. In PFL, a common strategy is to develop local and global models jointly - the global model (for generalization) informs the local models, and the local models (for personalization) are aggregated to update the global model. A key observation is that if we can improve the generalization ability of local models, then we can improve the generalization of global models, which in turn builds better personalized models. In this work, we consider class imbalance, an overlooked type of data heterogeneity, in the classification setting. We propose FedNH, a novel method that improves the local models' performance for both personalization and generalization by combining the uniformity and semantics of class prototypes. FedNH initially distributes class prototypes uniformly in the latent space and smoothly infuses the class semantics into class prototypes. We show that imposing uniformity helps to combat prototype collapse while infusing class semantics improves local models. Extensive experiments were conducted on popular classification datasets under the cross-device setting. Our results demonstrate the effectiveness and stability of our method over recent works.
translated by 谷歌翻译