内核方法是机器学习中最流行的技术之一,使用再现内核希尔伯特空间(RKHS)的属性来解决学习任务。在本文中,我们提出了一种新的数据分析框架,与再现内核Hilbert $ C ^ * $ - 模块(rkhm)和rkhm中的内核嵌入(kme)。由于RKHM包含比RKHS或VVRKHS)的更丰富的信息,因此使用RKHM的分析使我们能够捕获和提取诸如功能数据的结构属性。我们向RKHM展示了rkhm理论的分支,以适用于数据分析,包括代表性定理,以及所提出的KME的注射性和普遍性。我们还显示RKHM概括RKHS和VVRKHS。然后,我们提供采用RKHM和提议的KME对数据分析的具体程序。
translated by 谷歌翻译
With large-scale adaption to biometric based applications, security and privacy of biometrics is utmost important especially when operating in unsupervised online mode. This work proposes a novel approach for generating new artificial fingerprints also called proxy fingerprints that are natural looking, non-invertible, revocable and privacy preserving. These proxy biometrics can be generated from original ones only with the help of a user-specific key. Instead of using the original fingerprint, these proxy templates can be used anywhere with same convenience. The manuscripts walks through an interesting way in which proxy fingerprints of different types can be generated and how they can be combined with use-specific keys to provide revocability and cancelability in case of compromise. Using the proposed approach a proxy dataset is generated from samples belonging to Anguli fingerprint database. Matching experiments were performed on the new set which is 5 times larger than the original, and it was found that their performance is at par with 0 FAR and 0 FRR in the stolen key, safe key scenarios. Other parameters on revocability and diversity are also analyzed for protection performance.
translated by 谷歌翻译
Deep-learning-based technologies such as deepfakes ones have been attracting widespread attention in both society and academia, particularly ones used to synthesize forged face images. These automatic and professional-skill-free face manipulation technologies can be used to replace the face in an original image or video with any target object while maintaining the expression and demeanor. Since human faces are closely related to identity characteristics, maliciously disseminated identity manipulated videos could trigger a crisis of public trust in the media and could even have serious political, social, and legal implications. To effectively detect manipulated videos, we focus on the position offset in the face blending process, resulting from the forced affine transformation of the normalized forged face. We introduce a method for detecting manipulated videos that is based on the trajectory of the facial region displacement. Specifically, we develop a virtual-anchor-based method for extracting the facial trajectory, which can robustly represent displacement information. This information was used to construct a network for exposing multidimensional artifacts in the trajectory sequences of manipulated videos that is based on dual-stream spatial-temporal graph attention and a gated recurrent unit backbone. Testing of our method on various manipulation datasets demonstrated that its accuracy and generalization ability is competitive with that of the leading detection methods.
translated by 谷歌翻译
We present a lightweight post-processing method to refine the semantic segmentation results of point cloud sequences. Most existing methods usually segment frame by frame and encounter the inherent ambiguity of the problem: based on a measurement in a single frame, labels are sometimes difficult to predict even for humans. To remedy this problem, we propose to explicitly train a network to refine these results predicted by an existing segmentation method. The network, which we call the P2Net, learns the consistency constraints between coincident points from consecutive frames after registration. We evaluate the proposed post-processing method both qualitatively and quantitatively on the SemanticKITTI dataset that consists of real outdoor scenes. The effectiveness of the proposed method is validated by comparing the results predicted by two representative networks with and without the refinement by the post-processing network. Specifically, qualitative visualization validates the key idea that labels of the points that are difficult to predict can be corrected with P2Net. Quantitatively, overall mIoU is improved from 10.5% to 11.7% for PointNet [1] and from 10.8% to 15.9% for PointNet++ [2].
translated by 谷歌翻译
深度神经网络(DNN)众所周知,很容易受到对抗例子的影响(AES)。此外,AE具有对抗性可传递性,这意味着为源模型生成的AE可以以非平凡的概率欺骗另一个黑框模型(目标模型)。在本文中,我们首次研究了包括Convmixer在内的模型之间的对抗性转移性的属性。为了客观地验证可转让性的属性,使用称为AutoAttack的基准攻击方法评估模型的鲁棒性。在图像分类实验中,Convmixer被确认对对抗性转移性较弱。
translated by 谷歌翻译
深度神经网络(DNN)众所周知,很容易受到对抗例子的影响(AES)。此外,AE具有对抗性转移性,即为源模型傻瓜(目标)模型生成的AE。在本文中,我们首次研究了为对抗性强大防御的模型的可传递性。为了客观地验证可转让性的属性,使用称为AutoAttack的基准攻击方法评估模型的鲁棒性。在图像分类实验中,使用加密模型的使用不仅是对AE的鲁棒性,而且还可以减少AES在模型的可传递性方面的影响。
translated by 谷歌翻译
最近,在线广告客户使用推荐系统(RSS)来显示广告来改善用户的参与度。上下文强盗模型是一种广泛使用的RS,可利用和探索用户的参与度并最大化长期奖励,例如点击或转换。但是,当前的模型旨在仅在特定域中优化一组广告,并且不与多个域中的其他模型共享信息。在本文中,我们提出了动态协作过滤汤普森采样(DCTS),这是新颖而简单的模型,以在多个强盗模型之间传递知识。 DCT利用用户和广告之间的相似性来估计汤普森采样的先前分布。这种相似性是根据用户和广告的上下文功能获得的。相似性使模型在没有太多数据的域中通过传输知识来更快地收敛。此外,DCT结合了用户的时间动态,以跟踪用户最近的偏好变化。我们首先显示传递知识并结合时间动力学改善了合成数据集上基线模型的性能。然后,我们对现实世界数据集进行了经验分析,结果表明,与最先进的模型相比,DCTS的点击率提高了9.7%。我们还分析了调整时间动力学和相似性的超参数,并显示最大化CTR的最佳参数。
translated by 谷歌翻译
传统的神经结构倾向于通过类似数量(例如电流或电压)进行通信,但是,随着CMOS设备收缩和供应电压降低,电压/电流域模拟电路的动态范围变得更窄,可用的边缘变小,噪声免疫力降低。不仅如此,在常规设计中使用操作放大器(运算放大器)和时钟或异步比较器会导致高能量消耗和大型芯片区域,这将不利于构建尖峰神经网络。鉴于此,我们提出了一种神经结构,用于生成和传输时间域信号,包括神经元模块,突触模块和两个重量模块。所提出的神经结构是由晶体管三极区域的泄漏电流驱动的,不使用操作放大器和比较器,因此与常规设计相比,能够提供更高的能量和面积效率。此外,由于内部通信通过时间域信号,该结构提供了更大的噪声免疫力,从而简化了模块之间的接线。提出的神经结构是使用TSMC 65 nm CMOS技术制造的。拟议的神经元和突触分别占据了127 UM2和231 UM2的面积,同时达到了毫秒的时间常数。实际芯片测量表明,所提出的结构成功地用毫秒的时间常数实现了时间信号通信函数,这是迈向人机交互的硬件储层计算的关键步骤。
translated by 谷歌翻译
我们引入了责任感敏感安全性(RSS)的目标延长,这是一种基于规则的自动驾驶系统安全保证(ADS)的方法。制定RSS规则保证目标实现 - 除了原始RSS中的避免碰撞外,还需要进行长时间的操纵序列的复杂计划。为了应对复杂性,我们基于程序逻辑引入了一个构图推理框架,其中可以系统地为较小的子赛车制定RSS规则,并将它们组合起来以获取用于较大场景的RSS规则。作为框架的基础,我们介绍了一个程序逻辑DFHL,可满足连续的动态和安全条件。我们的框架介绍了基于DFHL的工作流程,用于导出目标感知RSS规则;我们也讨论其软件支持。我们在安全体系结构中使用RSS规则进行了实验评估。它的结果表明,目标感知RSS确实有效地实现了避免碰撞和目标实现目标。
translated by 谷歌翻译
我们已经调查了对抗性示例的新应用,即对地标识别系统的位置隐私保护。我们介绍了掩模引导的多模式投影梯度下降(MM-PGD),其中对抗示例在不同的深层模型上进行了培训。图像内容受到分析区域的特性,以识别最适合在对抗示例中混合的区域的性质。我们研究了两种区域识别策略:基于类激活图的MM-PGD,其中训练有素的深层模型的内部行为是针对的;和基于人视觉的MM-PGD,其中吸引人类注意力较少的地区的目标是针对的。Ploce365数据集的实验表明,这些策略在不需要大量图像操作的情况下可能有效地防御Black-Box Landmark识别系统。
translated by 谷歌翻译