Smart doorbells have been playing an important role in protecting our modern homes. Existing approaches of sending video streams to a centralized server (or Cloud) for video analytics have been facing many challenges ...
详细信息
ISBN:
(纸本)9781450388177
Smart doorbells have been playing an important role in protecting our modern homes. Existing approaches of sending video streams to a centralized server (or Cloud) for video analytics have been facing many challenges such as latency, bandwidth cost and more importantly users' privacy concerns. To address these challenges, this paper showcases the ability of an intelligent smart doorbell based on Federated Deep Learning, which can deploy and manage video analytics applications such as a smart doorbell across Edge and Cloud resources. This platform can scale, work with multiple devices, seamlessly manage online orchestration of the application components. The proposed framework is implemented using state-of-the-art technology. We implement the Federated Server using the Flask framework, containerized using Nginx and Gunicorn, which is deployed on AWS EC2 and AWS Serverless architecture.
FPGA-enabled cloud computing is getting more and more common as cloud providers offer hardware accelerated solutions. In this context, clients need confidential remote computing. However Intellectual Properties and da...
详细信息
ISBN:
(纸本)9781450391634
FPGA-enabled cloud computing is getting more and more common as cloud providers offer hardware accelerated solutions. In this context, clients need confidential remote computing. However Intellectual Properties and data are being used and communicated. So current security models require the client to trust the cloud provider blindly by disclosing sensitive information. In addition, the lack of strong authentication and access control mechanisms, for both the client and the provided FPGA in current solutions, is a major security drawback. To enhance security measures and privacy between the client, the cloud provider and the FPGA, an additional entity needs to be introduced: the trusted authority. Its role is to authenticate the client-FPGA pair and isolate them from the cloud provider. With our novel OAuth 2.0-based access delegation solution for FPGA-accelerated clouds, a remote confidential FPGA environment with a token-based access can be created for the client. Our solution allows to manage and securely allocate heterogeneous resource pools with enhanced privacy & confidentiality for the client. Our formal analysis shows that our protocol adds a very small latency which is suitable for real-time application.
The proceedings contain 41 papers. The topics discussed include: Ghostbuster: a fine-grained approach for anomaly detection in file system accesses;mining attributed graphs for threat intelligence;statistical security...
ISBN:
(纸本)9781450345231
The proceedings contain 41 papers. The topics discussed include: Ghostbuster: a fine-grained approach for anomaly detection in file system accesses;mining attributed graphs for threat intelligence;statistical security incident forensics against data falsification in smart grid advanced metering infrastructure;canonical completeness in lattice-based languages for attribute-based access control;SAMPAC: socially-aware collaborative multi-party access control;achieving differential privacy in secure multiparty data aggregation protocols on star networks;sound and static analysis of session fixation vulnerabilities in PHP web applications;a new bloom filter structure for searchable encryption schemes;seamless and secure Bluetooth LE connection migration;differentially-private big data analytics for high-speed research network traffic measurement;comprehensive method for detecting phishing emails using correlation-based analysis and user participation;PT-CFI: transparent backward-edge control flow violation detection using Intel processor trace;fault attacks on encrypted general purpose compute platforms;analysis of exception-based control transfers;detecting ROP with statistical learning of program characteristics;and large-scale identification of malicious singleton files.
暂无评论