Security- and Privacy-Aware Computing in Cloud With User Mobility

Today's computational model has been undergoing a huge paradigm shift from personalized, local processing using local processing unit (LPU) to remote processing at cloud servers located globally. Advances in sensor-based smart applications such as smart home, smart health, smart transport, smart environment monitoring, etc. are generating huge data which needs to stored, pre-processed, analyzed using machine learning and deep learning techniques, which are resource-hungry, to generate results to be saved for future reference, and all these need to be done in real time, with scalability support satisfying user data privacy and security that may vary from application to application. In smart application like remote health monitoring and support, patient data needs utmost privacy besides confidentiality, integrity, and availability.

A New System for Fake Profile Recognition in Social Networks

The billions of users all over the world are spending online social network, such as Twitter, Facebook, Tumbler and LinkedIn. The flaws in this social media may indications to abuse user’s information and execute an attack of identity cloning. In this work mainly focuses, a new method for hiding data to hide precise details in profile pictures to learn botnets and fake profiles. In this paper, presents an ordering and investigation of recognition mechanisms of genetic copy attacks on online network of social, purely established on attribute likeness, friend network likeness, and profile inquiry for a time interval and record of Internet Protocol sequences. This work, proposals an algorithm for transform discrete wavelet for hiding the data. So, the system can prevent the replica attacks and offer the whole user data privacy protective. Similarly, when users upload the profile image or photos it would be first watermarked and then updated. Java static watermarking systems and algorithms is been used for watermarking procedure. Here tracking any fake users updating the same profile picture given easier and tracking their IP address also became easier. Also, our system raises certain features which can be investigated to the users through process of registration. Thus, providing secure authentication. Hence avoiding clone attacks in social media became easier.

Security- and Privacy-Aware Computing in Cloud With User Mobility

Today's computational model has been undergoing a huge paradigm shift from personalized, local processing using local processing unit (LPU) to remote processing at cloud servers located globally. Advances in sensor-based smart applications such as smart home, smart health, smart transport, smart environment monitoring, etc. are generating huge data which needs to stored, pre-processed, analyzed using machine learning and deep learning techniques, which are resource-hungry, to generate results to be saved for future reference, and all these need to be done in real time, with scalability support satisfying user data privacy and security that may vary from application to application. In smart application like remote health monitoring and support, patient data needs utmost privacy besides confidentiality, integrity, and availability.

A homomorphic-encryption-based vertical federated learning scheme for rick management

With continuous improvements of computing power, great progresses in algorithms and massive growth of data, artificial intelligence technologies have entered the third rapid development era. However, With the great improvements in artificial intelligence and the arrival of the era of big data, contradictions between data sharing and user data privacy have become increasingly prominent. Federated learning is a technology that can ensure the user privacy and train a better model from different data providers. In this paper, we design a vertical federated learning system for the for Bayesian machine learning with the homomorphic encryption. During the training progress, raw data are leaving locally, and encrypted model information is exchanged. The model trained by this system is comparable (up to 90%) to those models trained by a single union server under the consideration of privacy. This system can be widely used in risk control, medical, financial, education and other fields. It is of great significance to solve data islands problem and protect users? privacy.

Demystifying User Data Privacy in the World of IOT

Internet of Things (IoT) would touch upon almost all aspects of everyday life, as a consequence of which, everything (i.e. living and non-living things) will have a counterpart virtual identities on the internet which would be readable, addressable and locatable. Although it would empower its users with 24×7 connectivity around the global world, unknowingly they would also provide it permission to peep into user’s personal world, which can generate a huge risk on the usability of IoT by users. Thus analyzing the framework of IOT from the perspective of user data protection is a very crucial self-test which is required for IoT implementation. Often the term security and privacy are used interchangeably, but in the IoT environment, both these concept would play a crucial but differentiating role. In this paper, we have scanned the IoT environment with the perspective of privacy requirements, possible threats and the mitigating solutions which are currently in use.

Traffic model using a novel sniffer that ensures the user data privacy

Nowadays, the traffic over the networks is changing because of new protocols, devices and applications. Therefore, it is necessary to analyze the impact over services and resources. Traffic Classification of network is a very important prerequisite for tasks such as traffic engineering and provisioning quality of service. In this paper, we analyze the variable packet size of the traffic in an university campus network through the collected data using a novel sniffer that ensures the user data privacy. We separate the collected data by type of traffic, protocols and applications. Finally, we estimate the traffic model that represents this traffic by means of a Poisson process and compute its associated numerical parameters.