Is software that lets you run local compute messaging data caching sync and machine learning inference capabilities for connected devices in a secure way?
Answers from top 8 papers
More filters
Papers (8) | Insight |
---|---|
01 Dec 2018 39 Citations | The use of in-network caching in ICN enhances the data availability in the network, overcomes the issue of single-point failure, and improves IoT devices power efficiency. |
37 Citations | In such applications, caching data at some edge devices can greatly improve data availability, retrieval robustness, and delivery latency. |
Caching of frequently accessed data in multi-hop ad hoc environment is a potential technique that can improve the data access performance and availability. | |
01 Dec 2018 116 Citations | In order to address this issue, we propose a Federated learning based Proactive Content Caching (FPCC) scheme, which does not require to gather users' data centrally for training. |
34 Citations | This article proposes a novel deep learning-based proactive caching framework in cellular networks, called DeepCachNet, in which a vast amount of data is collected from the mobile devices of users connected to SBSs. |
52 Citations | However, the caching management is a challenging and complex task, especially in those scenarios of shared storage resources on edge devices to support multiple concurrent applications (e. g., industrial, mobile users, and connected cars applications). |
The optimal data caching strategy in the edge computing environment will minimize the data caching cost while maximizing the reduction in service latency. | |
09 May 2005 | In this paper, we propose a novel approach for caching multidimensional data in a cluster of mobile devices. |
Related Questions
How can machine learning and deep learning algorithms be used to improve the security of computer systems and networks?4 answersMachine learning and deep learning algorithms can be used to improve the security of computer systems and networks in several ways. These algorithms can help in real-time active attack prevention, protecting against security breaches, malware, and viruses, and providing more accurate network protection. They can also be used to monitor and prevent network attacks, identify system irregularities that may signal an ongoing attack, and make systems safer. Various machine learning and deep learning algorithms, such as regression, clustering, classification, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and LSTM plus CNN, have been employed to enhance cybersecurity. These algorithms have shown promising results in detecting multiple attacks and defending against external or internal threats to the network.
Exist there AI, which can be local hosted and trained with own data?5 answersThere are AI systems that can be locally hosted and trained with their own data. These systems allow users to train machine learning models on their local datasets and preserve data privacy. One approach to distributed machine learning is federated learning, where local models are trained on individual devices and then aggregated into a single, stronger model. Another approach involves co-designing AI systems with local communities, empowering them to address regional concerns and collect and explain community data using AI. Additionally, radiologist-trained AI models have been developed to differentiate between suboptimal and optimal chest radiographs, enabling radiographers to repeat suboptimal images when necessary. In the context of a permissionless AI marketplace, there is a platform that allows data providers, virtual servers, and AI designers to collaborate and protect data access and security while training AI models.
What research paper exist that focus on security for mobile using machine learning?5 answersMobile network payment gateways have become more accessible to consumers, leading to the need for security measures such as malware detection, authentication, and fraud detection. A recommended solution is the Secure Mobile Electronic Payment Framework Enhanced by Machine Learning. The rapid growth of Android smartphones and applications has also raised security concerns, particularly in detecting malware applications. A proposed solution is the DeepAutoD framework, which uses deep deception call chains to detect malicious code in a short time. Advancements in wireless communication technologies have resulted in increased security breaches in mobile networks. To address this, an artificial intelligence-based security model is suggested to ensure the secrecy, integrity, and authenticity of the system. Mobile authentication using behavioral biometrics is another area of research, with a focus on improving discriminative features and addressing challenges such as data privacy and side-channel leaks. In the context of IoT systems, machine learning techniques are being used to manage security aspects and detect attacks, with the Random Forest algorithm achieving high accuracy.
How does quantum computing help overcome the limitations of machine learning in the field of ransomware detection?5 answersQuantum computing helps overcome the limitations of machine learning in the field of ransomware detection by providing faster and more accurate detection methods. The use of quantum machine learning (QML) algorithms, such as Quantum Support Vector Machine (QSVM) and Quantum Convolutional Neural Network (QCNN), allows for high-performance intrusion detection with big data inputs. QML-based intrusion detection has been shown to process big data inputs with high accuracy (98%) and twice the speed of conventional machine learning algorithms. Additionally, the combination of quantum information and machine learning techniques can enhance the security and privacy of machine learning models. Quantum technologies can be used to make quantum classifiers more secure and private, as well as provide advantages in bagging and boosting methods.
How can we use machine learning to improve the security of cloud computing?4 answersMachine learning (ML) techniques are being used to improve the security of cloud computing. ML is used to prevent or detect attacks and security gaps in the cloud. ML models play an essential role in addressing security issues such as real-time attack detection, data leakage vulnerability assessments, and adversarial attacks. ML algorithms are used to make real-time decisions, process big data, reduce cycle time for learning, and ensure cost-efficiency and error-free processing. ML is also used in Machine Learning as a Service (MLaaS) cloud platforms, which have become popular for offering efficient and cost-effective services. Researchers are focusing on both attacking and defending different attacks on MLaaS platforms. However, there are still open research issues that require further investigation in this area.
What advantages do you get by running inference on a server instead of distributing the model to all your clients?14 answers