机器学习模型容易对远离培训分布的投入进行错误的预测。这阻碍了他们在自动驾驶汽车和医疗保健等安全至关重要应用中的部署。从单个数据点的训练分布转移的检测引起了人们的注意。已经提出了许多用于分发（OOD）检测的技术。但是在许多应用中，机器学习模型的输入形成了时间序列。时间序列数据中的OOD检测技术要么不利用序列中的时间关系，要么不提供任何检测保证。我们建议将偏离分布式时间均衡力偏差作为在时间序列数据中进行OOD检测的保形异常检测框架中的不符合度量度。导致提议的检测器编码，并保证在时间序列数据中进行虚假检测。我们通过在自动驾驶中实现计算机视觉数据集的最新结果来说明编码的功效。我们还表明，通过在生理步态感觉数据集上执行实验，可以将CODIT用于非视觉数据集中的OOD检测。代码，数据和训练有素的模型可在https://github.com/kaustubhsridhar/time-series-ood上找到。

共同的意图是开发能够协作，自我反思，审议和推理的有意识的AI代理的关键组成部分。我们将共同意图的推论作为逻辑奖励规范的反向加强学习问题。我们展示了该方法如何从演示中推断任务描述。我们还扩展了积极传达意图的方法。我们在一个简单的网格世界示例上演示了该方法。

我们研究了分布外（OOD）检测的问题，也就是说，检测学习算法的输出是否可以在推理时间得到信任。尽管已经在先前的工作中提出了许多OOD检测的测试，但缺乏研究此问题的正式框架。我们提出了一个关于OOD概念的定义，其中包括输入分布和学习算法，该算法为构建强大的OOD检测测试提供了见解。我们提出了一个多个假设测试的启发程序，以系统地结合学习算法的任何数量的不同统计数据，使用保形p值。我们进一步为将分配样本分类为OOD的概率提供了强有力的保证。在我们的实验中，我们发现在先前工作中提出的基于阈值的测试在特定的设置中表现良好，但在不同类型的OOD实例中并不均匀。相比之下，我们提出的方法结合了多个统计数据在不同的数据集和神经网络中表现出色。

诸如深神经网络（DNN）之类的机器学习方法，尽管他们在不同域中取得了成功，但是众所周知，通常在训练分布之外的输入上具有高信心产生不正确的预测。在安全关键域中的DNN部署需要检测分配超出（OOD）数据，以便DNN可以避免对那些人进行预测。最近已经开发了许多方法，以便检测，但仍有改进余地。我们提出了新的方法IdeCode，利用了用于共形OOD检测的分销标准。它依赖于在电感共形异常检测框架中使用的新基础非符合性测量和新的聚合方法，从而保证了有界误报率。我们通过在图像和音频数据集上的实验中展示了IDecode的功效，获得了最先进的结果。我们还表明Idecode可以检测对抗性示例。

深度学习的成功使得能够在需要多模式任务中的进步，这些任务需要非普通融合多个输入域。尽管多式联运模型在许多问题中表现出潜力，但它们的复杂性增加使它们更容易攻击。后门（或特洛伊木马）攻击是一类安全漏洞，其中攻击者将恶意秘密行为嵌入到网络（例如目标错误分类）中，当攻击者指定的触发添加到输入时被激活。在这项工作中，我们表明多模态网络容易受到我们称之为双关键多模式后域的新型攻击。该攻击利用最先进的网络使用的复杂融合机制来嵌入有效和隐秘的后门。该建议的攻击而不是使用单个触发器，而不是使用单个触发器在每个输入模件中嵌入触发器，并仅在存在两种触发时激活恶意行为。我们对具有多个体系结构和视觉功能底座的视觉问题应答（VQA）任务进行了广泛的研究。在VQA模型中嵌入后门的一项重大挑战是，大多数模型都使用从固定的预磨削物体检测器中提取的可视化特征。这对攻击者有挑战性，因为探测器完全扭曲或忽略视觉触发，这导致了后域在语言触发上过于依赖的模型。我们通过提出为预磨料对象探测器设计的可视触发优化策略来解决这个问题。通过这种方法，我们创建双关键的返回室，超过98％的攻击成功率，同时只毒害了1％的培训数据。最后，我们发布了Trojvqa，大量的干净和特洛伊木马VQA模型，以实现对多模式后域的捍卫的研究。

The rapid development of remote sensing technologies have gained significant attention due to their ability to accurately localize, classify, and segment objects from aerial images. These technologies are commonly used in unmanned aerial vehicles (UAVs) equipped with high-resolution cameras or sensors to capture data over large areas. This data is useful for various applications, such as monitoring and inspecting cities, towns, and terrains. In this paper, we presented a method for classifying and segmenting city road traffic dashed lines from aerial images using deep learning models such as U-Net and SegNet. The annotated data is used to train these models, which are then used to classify and segment the aerial image into two classes: dashed lines and non-dashed lines. However, the deep learning model may not be able to identify all dashed lines due to poor painting or occlusion by trees or shadows. To address this issue, we proposed a method to add missed lines to the segmentation output. We also extracted the x and y coordinates of each dashed line from the segmentation output, which can be used by city planners to construct a CAD file for digital visualization of the roads.

Though impressive success has been witnessed in computer vision, deep learning still suffers from the domain shift challenge when the target domain for testing and the source domain for training do not share an identical distribution. To address this, domain generalization approaches intend to extract domain invariant features that can lead to a more robust model. Hence, increasing the source domain diversity is a key component of domain generalization. Style augmentation takes advantage of instance-specific feature statistics containing informative style characteristics to synthetic novel domains. However, all previous works ignored the correlation between different feature channels or only limited the style augmentation through linear interpolation. In this work, we propose a novel augmentation method, called \textit{Correlated Style Uncertainty (CSU)}, to go beyond the linear interpolation of style statistic space while preserving the essential correlation information. We validate our method's effectiveness by extensive experiments on multiple cross-domain classification tasks, including widely used PACS, Office-Home, Camelyon17 datasets and the Duke-Market1501 instance retrieval task and obtained significant margin improvements over the state-of-the-art methods. The source code is available for public use.

Time-of-flight (ToF) distance measurement devices such as ultrasonics, LiDAR and radar are widely used in autonomous vehicles for environmental perception, navigation and assisted braking control. Despite their relative importance in making safer driving decisions, these devices are vulnerable to multiple attack types including spoofing, triggering and false data injection. When these attacks are successful they can compromise the security of autonomous vehicles leading to severe consequences for the driver, nearby vehicles and pedestrians. To handle these attacks and protect the measurement devices, we propose a spatial-temporal anomaly detection model \textit{STAnDS} which incorporates a residual error spatial detector, with a time-based expected change detection. This approach is evaluated using a simulated quantitative environment and the results show that \textit{STAnDS} is effective at detecting multiple attack types.

Recently, automated co-design of machine learning (ML) models and accelerator architectures has attracted significant attention from both the industry and academia. However, most co-design frameworks either explore a limited search space or employ suboptimal exploration techniques for simultaneous design decision investigations of the ML model and the accelerator. Furthermore, training the ML model and simulating the accelerator performance is computationally expensive. To address these limitations, this work proposes a novel neural architecture and hardware accelerator co-design framework, called CODEBench. It is composed of two new benchmarking sub-frameworks, CNNBench and AccelBench, which explore expanded design spaces of convolutional neural networks (CNNs) and CNN accelerators. CNNBench leverages an advanced search technique, BOSHNAS, to efficiently train a neural heteroscedastic surrogate model to converge to an optimal CNN architecture by employing second-order gradients. AccelBench performs cycle-accurate simulations for a diverse set of accelerator architectures in a vast design space. With the proposed co-design method, called BOSHCODE, our best CNN-accelerator pair achieves 1.4% higher accuracy on the CIFAR-10 dataset compared to the state-of-the-art pair, while enabling 59.1% lower latency and 60.8% lower energy consumption. On the ImageNet dataset, it achieves 3.7% higher Top1 accuracy at 43.8% lower latency and 11.2% lower energy consumption. CODEBench outperforms the state-of-the-art framework, i.e., Auto-NBA, by achieving 1.5% higher accuracy and 34.7x higher throughput, while enabling 11.0x lower energy-delay product (EDP) and 4.0x lower chip area on CIFAR-10.

Point Cloud Registration is the problem of aligning the corresponding points of two 3D point clouds referring to the same object. The challenges include dealing with noise and partial match of real-world 3D scans. For non-rigid objects, there is an additional challenge of accounting for deformations in the object shape that happen to the object in between the two 3D scans. In this project, we study the problem of non-rigid point cloud registration for use cases in the Augmented/Mixed Reality domain. We focus our attention on a special class of non-rigid deformations that happen in rigid objects with parts that move relative to one another about joints, for example, robots with hands and machines with hinges. We propose an efficient and robust point-cloud registration workflow for such objects and evaluate it on real-world data collected using Microsoft Hololens 2, a leading Mixed Reality Platform.