The cloud computing landscape has evolved significantly in recent years, embracing various sandboxes to meet the diverse demands of modern cloud applications. These sandboxes encompass container-based technologies like Docker and gVisor, microVM-based solutions like Firecracker, and security-centric sandboxes relying on Trusted Execution Environments (TEEs) such as Intel SGX and AMD SEV. However, the practice of placing multiple tenants on shared physical hardware raises security and privacy concerns, most notably side-channel attacks. In this paper, we investigate the possibility of fingerprinting containers through CPU frequency reporting sensors in Intel and AMD CPUs. One key enabler of our attack is that the current CPU frequency information can be accessed by user-space attackers. We demonstrate that Docker images exhibit a unique frequency signature, enabling the distinction of different containers with up to 84.5% accuracy even when multiple containers are running simultaneously in different cores. Additionally, we assess the effectiveness of our attack when performed against several sandboxes deployed in cloud environments, including Google's gVisor, AWS' Firecracker, and TEE-based platforms like Gramine (utilizing Intel SGX) and AMD SEV. Our empirical results show that these attacks can also be carried out successfully against all of these sandboxes in less than 40 seconds, with an accuracy of over 70% in all cases. Finally, we propose a noise injection-based countermeasure to mitigate the proposed attack on cloud environments.

In an increasingly automated world -- from warehouse robots to self-driving cars -- streamlining the development and deployment process and operations of robotic applications becomes ever more important. Automated DevOps processes and microservice architectures have already proven successful in other domains such as large-scale customer-oriented web services (e.g., Netflix). We recommend to employ similar microservice architectures for the deployment of small- to large-scale robotic applications in order to accelerate development cycles, loosen functional dependence, and improve resiliency and elasticity. In order to facilitate involved DevOps processes, we present and release a tooling suite for automating the development of microservices for robotic applications based on the Robot Operating System (ROS). Our tooling suite covers the automated minimal containerization of ROS applications, a collection of useful machine learning-enabled base container images, as well as a CLI tool for simplified interaction with container images during the development phase. Within the scope of this paper, we embed our tooling suite into the overall context of streamlined robotics deployment and compare it to alternative solutions. We release our tools as open-source software at https://github.com/ika-rwth-aachen/dorotos.

Let MindsDB connect to your database. Train a Predictor using a single SQL statement (make MindsDB learn from historical data automatically) or import your ML model to a Predictor via JSON-AI. Make predictions with SQL statements (Predictor is exposed as virtual AI Tables). There's no need to deploy models since they are already part of the data layer. Check our docs and blog for tutorials and use case examples. MindsDB works with most of the SQL and NoSQL databases and data Streams for real-time ML.

This is a project that is organized by Datatalks.Club. In this competition, one has to train a deep learning model in tensorflow or pytorch to classify kitchenware items. I used tensorflow and keras for this task. As an image classification model, when given the image of one of the above-listed kitchenware items, the model will output probailities for each of the six classes. The highest probability serves as the model's final classification.

Following the development of digitization, a growing number of large Original Equipment Manufacturers (OEMs) are adapting computer vision or natural language processing in a wide range of applications such as anomaly detection and quality inspection in plants. Deployment of such a system is becoming an extremely important topic. Our work starts with the least-automated deployment technologies of machine learning systems includes several iterations of updates, and ends with a comparison of automated deployment techniques. The objective is, on the one hand, to compare the advantages and disadvantages of various technologies in theory and practice, so as to facilitate later adopters to avoid making the generalized mistakes when implementing actual use cases, and thereby choose a better strategy for their own enterprises. On the other hand, to raise awareness of the evaluation framework for the deployment of machine learning systems, to have more comprehensive and useful evaluation metrics (e.g. table 2), rather than only focusing on a single factor (e.g. company cost). This is especially important for decision-makers in the industry.

FastAPI is a new Python-based web framework used to create Web APIs. FastAPI is fast when serving your application, also enhances the performance of our application. Note: for you to follow along easily, use Google Colab. It's an easy-to-use platform to get started quickly while building models. We will build a machine learning model that will predict the nationality of individuals using their names. This is a simple model that will explain the key concepts used in machine learning modeling. The dataset used will contains common names of people and their nationalities. Pandas is a software library written for the Python programming language for data manipulation and analysis.

Creating a model is one thing, but using that model in production is quite another. The next step after a data scientist completes a model is to deploy it so that it can serve the application. Batch and online model serving are the two main categories. Batch refers to feeding a large amount of data into a model and writing the results to a table, usually as a scheduled operation. You must deploy the model online using an endpoint for applications to send a request to the model and receive a quick response with no latency.

It was introduced in the paper DiT: Self-supervised Pre-training for Document Image Transformer by Li et al. and first released in this repository. Note that DiT is identical to the architecture of BEiT. An application program interface (API) is a set of routines, protocols, and tools for building software applications. Basically, an API specifies how software components should interact. FastAPI is a Web framework for developing RESTful APIs in Python.

With many organisations focusing research on enhancing AI capabilities, we see a lot of action and breakthroughs in the world of deep learning. Most state-of-the-art models are being open-sourced on TFHub, HuggingFace & PyTorch for everyone to experiment and enjoy. Yet, most of these models are heavy and not much useful for CPU based inference and deployments. We improved our inference speed and reduced the size of our docker image from 9.7 Gb to 3.7 Gb (3x reduction), which serves as the motivation for this article. In this article, we would like to present some of the best practices and tricks we followed deploying deep learning models on the cloud using Docker.

In this article, you learn how to create and run machine learning pipelines by using the Azure Machine Learning SDK. Use ML pipelines to create a workflow that stitches together various ML phases. Then, publish that pipeline for later access or sharing with others. Track ML pipelines to see how your model is performing in the real world and to detect data drift. ML pipelines are ideal for batch scoring scenarios, using various computes, reusing steps instead of rerunning them, and sharing ML workflows with others. For guidance on creating your first pipeline, see Tutorial: Build an Azure Machine Learning pipeline for batch scoring or Use automated ML in an Azure Machine Learning pipeline in Python.