通过无线网络互联设备数量和数据通信数量的显着增加引起了各种威胁，风险和安全问题。物联网（IoT）应用程序几乎部署在日常生活中的几乎所有领域，包括敏感环境。边缘计算范例通过在数据源附近移动计算处理来补充了IOT应用程序。在各种安全模型中，基于机器学习（ML）的入侵检测是最可想到的防御机制，用于打击已启用边缘的物联网中的异常行为。 ML算法用于将网络流量分类为正常和恶意攻击。入侵检测是网络安全领域的具有挑战性问题之一。研究界提出了许多入侵检测系统。然而，选择合适的算法涉及在启用边缘的物联网网络中提供安全性的挑战存在。在本文中，已经执行了传统机器学习分类算法的比较分析，以在Puparm工具上使用Jupyter对NSL-KDD数据集上的网络流量进行分类。可以观察到，多层感知（MLP）在输入和输出之间具有依赖性，并且更多地依赖于用于入侵检测的网络配置。因此，MLP可以更适合于基于边缘的物联网网络，其具有更好的培训时间为1.2秒，测试精度为79％。

A comprehensive pharmaceutical recommendation system was designed based on the patients and drugs features extracted from Drugs.com and Druglib.com. First, data from these databases were combined, and a dataset of patients and drug information was built. Secondly, the patients and drugs were clustered, and then the recommendation was performed using different ratings provided by patients, and importantly by the knowledge obtained from patients and drug specifications, and considering drug interactions. To the best of our knowledge, we are the first group to consider patients conditions and history in the proposed approach for selecting a specific medicine appropriate for that particular user. Our approach applies artificial intelligence (AI) models for the implementation. Sentiment analysis using natural language processing approaches is employed in pre-processing along with neural network-based methods and recommender system algorithms for modeling the system. In our work, patients conditions and drugs features are used for making two models based on matrix factorization. Then we used drug interaction to filter drugs with severe or mild interactions with other drugs. We developed a deep learning model for recommending drugs by using data from 2304 patients as a training set, and then we used data from 660 patients as our validation set. After that, we used knowledge from critical information about drugs and combined the outcome of the model into a knowledge-based system with the rules obtained from constraints on taking medicine.

Adversarial training is an effective approach to make deep neural networks robust against adversarial attacks. Recently, different adversarial training defenses are proposed that not only maintain a high clean accuracy but also show significant robustness against popular and well studied adversarial attacks such as PGD. High adversarial robustness can also arise if an attack fails to find adversarial gradient directions, a phenomenon known as `gradient masking'. In this work, we analyse the effect of label smoothing on adversarial training as one of the potential causes of gradient masking. We then develop a guided mechanism to avoid local minima during attack optimization, leading to a novel attack dubbed Guided Projected Gradient Attack (G-PGA). Our attack approach is based on a `match and deceive' loss that finds optimal adversarial directions through guidance from a surrogate model. Our modified attack does not require random restarts, large number of attack iterations or search for an optimal step-size. Furthermore, our proposed G-PGA is generic, thus it can be combined with an ensemble attack strategy as we demonstrate for the case of Auto-Attack, leading to efficiency and convergence speed improvements. More than an effective attack, G-PGA can be used as a diagnostic tool to reveal elusive robustness due to gradient masking in adversarial defenses.

Although existing semi-supervised learning models achieve remarkable success in learning with unannotated in-distribution data, they mostly fail to learn on unlabeled data sampled from novel semantic classes due to their closed-set assumption. In this work, we target a pragmatic but under-explored Generalized Novel Category Discovery (GNCD) setting. The GNCD setting aims to categorize unlabeled training data coming from known and novel classes by leveraging the information of partially labeled known classes. We propose a two-stage Contrastive Affinity Learning method with auxiliary visual Prompts, dubbed PromptCAL, to address this challenging problem. Our approach discovers reliable pairwise sample affinities to learn better semantic clustering of both known and novel classes for the class token and visual prompts. First, we propose a discriminative prompt regularization loss to reinforce semantic discriminativeness of prompt-adapted pre-trained vision transformer for refined affinity relationships. Besides, we propose a contrastive affinity learning stage to calibrate semantic representations based on our iterative semi-supervised affinity graph generation method for semantically-enhanced prompt supervision. Extensive experimental evaluation demonstrates that our PromptCAL method is more effective in discovering novel classes even with limited annotations and surpasses the current state-of-the-art on generic and fine-grained benchmarks (with nearly $11\%$ gain on CUB-200, and $9\%$ on ImageNet-100) on overall accuracy.

Entity matching in Customer 360 is the task of determining if multiple records represent the same real world entity. Entities are typically people, organizations, locations, and events represented as attributed nodes in a graph, though they can also be represented as records in relational data. While probabilistic matching engines and artificial neural network models exist for this task, explaining entity matching has received less attention. In this demo, we present our Explainable Entity Matching (xEM) system and discuss the different AI/ML considerations that went into its implementation.

物体重新识别（REID）是生物识别和监视系统中最重要的问题之一，在过去几十年来通过图像处理和计算机视觉社区进行了广泛的研究。学习强大而判别的特征表示是对象REID的关键挑战。在REID中，基于无人机（UAV）的REID更具挑战性，因为图像的特征是飞行无人机的摄像机参数（例如，视角，海拔等）的连续变化。为了应对这一挑战，已经考虑了多尺度特征表示形式来表征来自不同海拔无人机飞行的图像。在这项工作中，我们提出了一种多任务学习方法，该方法采用新的多尺度体系结构，无卷积，金字塔视觉变压器（PVT），作为基于无人机的对象REID的骨干。通过对类内变化的不确定性建模，我们提出的模型可以使用不确定性感知对象ID和相机ID信息共同优化。实验结果报告了Prai和VRAI，这是两个REID数据集，从空中监视中验证我们提出的方法的有效性

混合精确的深神经网络达到了硬件部署所需的能源效率和吞吐量，尤其是在资源有限的情况下，而无需牺牲准确性。但是，不容易找到保留精度的最佳每层钻头精度，尤其是在创建巨大搜索空间的大量模型，数据集和量化技术中。为了解决这一困难，最近出现了一系列文献，并且已经提出了一些实现有希望的准确性结果的框架。在本文中，我们首先总结了文献中通常使用的量化技术。然后，我们对混合精液框架进行了彻底的调查，该调查是根据其优化技术进行分类的，例如增强学习和量化技术，例如确定性舍入。此外，讨论了每个框架的优势和缺点，我们在其中呈现并列。我们最终为未来的混合精液框架提供了指南。

最近，已经提出了几种领域的概括（DG）方法，表现出令人鼓舞的性能，但是，几乎所有的都基于卷积神经网络（CNN）。研究视觉变压器（VIT）的DG性能（VIT）几乎没有进展，这挑战了CNN在标准基准测试基准上的至高无上，通常是基于I.I.D假设。这使VITS的现实部署令人怀疑。在本文中，我们试图探索解决DG问题的VIT。与CNN类似，VIT在分发场景中也挣扎，主要的罪魁祸首过于适合来源域。受VIT的模块化体系结构的启发，我们提出了一种简单的DG方法，用于VIT，以VIT的自我验证。它通过策划中间变压器块的非零熵监管信号来减少输入输出映射问题的学习来减少源域的过度拟合。此外，它不会引入任何新参数，并且可以无缝地插入不同VIT的模块化组成中。我们在五个具有挑战性的数据集中以不同的DG基准和各种VIT骨架表现出显着的性能提高。此外，我们报告了针对最近最新的DG方法的有利性能。我们的代码以及预培训的模型可在以下网址公开获取：https：//github.com/maryam089/sdvit

Pansharpening使用高空间分辨率Panchromatic图像的特征增强了高光谱分辨率多光谱图像的空间细节。有许多传统的pansharpening方法，但是产生表现出高光谱和空间保真度的图像仍然是一个空旷的问题。最近，深度学习已被用来产生有希望的Pansharped图像。但是，这些方法中的大多数通过使用相同的网络进行特征提取，对多光谱和全球性图像都采用了类似的处理。在这项工作中，我们提出了一个新型的基于双重注意的两流网络。首先使用两个单独的网络进行两个图像的特征提取，这是一种具有注意机制的编码器，可重新校准提取的功能。接下来是融合的特征，形成喂入图像重建网络的紧凑表示形式以产生pansharped图像。使用标准定量评估指标和视觉检查的PL \'{E} IADES数据集的实验结果表明，就Pansharped图像质量而言，所提出的方法比其他方法更好。

可转移的对抗性攻击优化了从验证的替代模型和已知标签空间中的对手，以欺骗未知的黑盒模型。因此，这些攻击受到有效的替代模型的可用性受到限制。在这项工作中，我们放宽了这一假设，并提出了对抗像素的恢复，作为一种自制的替代方案，可以在无标签和很少的数据样本的条件下从头开始训练有效的替代模型。我们的培训方法是基于一个最小目标的目标，该目标通过对抗目标减少过度拟合，从而为更概括的替代模型进行了优化。我们提出的攻击是对对抗性像素恢复的补充，并且独立于任何特定任务目标，因为它可以以自我监督的方式启动。我们成功地证明了我们对视觉变压器方法的对抗性可传递性以及卷积神经网络，用于分类，对象检测和视频分割的任务。我们的代码和预培训的代理模型可在以下网址找到：https：//github.com/hashmatshadab/apr