Lucas Airam C. de Souza

Abstract: The effectiveness of machine learning systems depends heavily on the relevance of the training data. Usually, the collected data is sensitive and private because it comes from devices and sensors used in people's daily lives. The General Data Protection Regulation (GDPR) in Europe, the California Consumer Privacy Act (CCPA) in California, and China's Cybersecurity Law put the current approach at risk, as it prohibits centralized remote processing of sensitive data collected in a distributed manner. This paper proposes a distributed machine learning system based on local random forest algorithms created with shared decision trees through the blockchain. The results show that the proposed approach equals or exceeds the results obtained with the use of random forests with only local data. Furthermore, the proposal increases the detection of new attacks when the domains have different threat distributions.

Abstract: The trust centralization in current data sharing systems restricts the owner's control over their data. Furthermore, the owner's intervention to authorize his/hers data access for each request makes frequent access to popular data tiresome. In this paper, we propose AutAvailChain, an architecture based on software defined networking (SDN) and blockchain to provide secure, automatic, and distributed sharing of IoT data. We develop a prototype using the Hyperledger Fabric platform to implement the blockchain and a smart contract. The results show a quick, secure, and excellent performance of dozens of transactions per second.

Every citizen has the right to privacy and, therefore, the right to control their personal information, deciding to whom, when, and where their information is available. This paper proposes a secure, agile, and effective system for a distributed, automatic, and transparent data trading between domains using blockchain, smart contracts, trust, and reputation. We develop and implement a prototype of a trust and reputation system based on real-life interactions. The results show that the proposed system provides security and privacy in a quick and distributed way, performing hundreds of transactions per second, and effectively punishing malicious behavior.

Abstract: Cybernetic attacks have been increasingly common and cause great harm to people and organizations. Late detection of such attacks increases the possibility of irreparable damage, with high financial losses being a common occurrence. This article proposes TeMIA-NT (ThrEat Monitoring and Intelligent data Analytics of Network Traffic), a real-time flow analysis system that uses parallel flow processing. The main contributions of the TeMIA-NT are: i) the proposal of an architecture for realtime detection of network intrusions that supports high traffic rates, ii) the use of the structured streaming library, and iii) two modes of operation: offline and online. The offline operation mode allows evaluating the performance of multiple machine learning algorithms over a given dataset, including metrics such as accuracy, F1-score, and area under the curve (AUC). The proposal uses dataframe structures, in online mode, the structured streaming library in continuous mode, which allows detection of threats in real-time and a quick reaction to attacks. To prevent or minimize the damage caused by security attacks, TeMIA-NT achieves flow-processing rates that reach 50 GB/s.

Abstract: Network slicing, network function virtualization (NFV), and software defined network (SDN) technologies provide agile on-demand end-to-end services. The identification of a faulty virtual function becomes mandatory because services allocate resources across a distributed and trustless environment composed by multi-tenant competing service providers. In this paper, we propose and develop a blockchain-based architecture to provide auditability to orchestration operations of network slices and to provide secure VNF configuration updates while ensuring isolation and privacy between network slices. A proof of concept prototype using the Hyperledger Fabric platform was developed in which network slice runs on an isolated channel. The results show that we can secure a network slice creation, but that the consensus and the number of transaction required by the slices are a great challenge.