Federated Learning has rapidly expanded from its original inception to now have a large body of research, several frameworks, and sold in a variety of commercial offerings. Thus, its security and robustness is of significant importance. There are many algorithms that provide robustness in the case of malicious clients. However, the aggregator itself may behave maliciously, for example, by biasing the model or tampering with the weights to weaken the model’s privacy. In this work, we introduce a verifiable federated learning protocol that enables clients to verify the correctness of the aggregator’s computation without compromising the confidentiality of their updates. Our protocol uses a standard secure aggregation technique to protect individual model updates with a linearly homomorphic authenticator scheme that enables efficient, privacy-preserving verification of the aggregated result. Our construction ensures that clients can detect manipulation by the aggregator while maintaining low computational overhead. We demonstrate that our approach scales to large models, enabling verification over large neural networks with millions of parameters.

The evolving complexity of modern IT infrastructures has paved the way for malicious actors to exploit a wide array of vulnerabilities that can compromise the integrity of these systems. Monitoring complex IT systems is expensive and often requires dedicated infrastructure for deploying Intrusion and/or Anomaly Detection Systems. Moreover, ML-based solutions need large training sets, which add to the overall cost. To tackle these challenges we present INTELLECT, a novel approach to Intrusion and/or Anomaly Detection System, which leverages Federated Learning and model pruning techniques to cooperatively train high-accuracy models using distributed datasets and derive a fleet of lightweight models, which can be deployed without incurring additional costs for dedicated infrastructure. INTELLECT expands on the state-of-the-art techniques for feature selection, model pruning, and model distillation to create an interconnected pipeline. We empirically demonstrate the effectiveness of the methodology on benchmark datasets, and we present guidelines for the deployment in production systems.

Person-specific data offer enormous opportunities for deriving insights that can radically improve different facets of our everyday lives, ranging from the provisioning of personalized medicine and healthcare, to the offering of smart transportation and smart energy. At the same time, the use of person-specific data to support these applications can come at a high cost to individuals' privacy, unless proper de-identification technology is in place to provide rigorous privacy guarantees. In this paper we introduce PRIMA, an end-to-end solution allowing decision makers to map out and execute their data privacy strategy through a comprehensive workflow. Our toolkit offers an intuitive risk-utility exploration framework for end users to navigate through the enormous number of possible combinations of anonymization settings and provide meaningful reports that help them understand the impact of each strategy in terms of utility and risk. Unlike traditional approaches, that rely on limited scale tools and manual analyses, our toolkit is the first scalable, production-grade system that can execute all of its components (such as vulnerability analysis, anonymization, risk and information loss measurements) on arbitrarily large datasets. Furthermore, it offers a flexible library for developers to integrate and extend its functionality to embed de-identification components into their applications.

It is often necessary to compose a team consisting of experts with diverse competencies to accomplish complex tasks. However, for its proper functioning, it is also preferable that a team be socially cohesive. A team recommendation system, which facilitates the search for potential team members, can be of great help both for (a) individuals who need to seek out collaborators and for (b) managers who need to build a team for some specific tasks. Such a decision support system that readily helps summarize multiple metrics indicating a team (and its members) quality, and possibly rank the teams in a personalized manner according to the end users' preferences, thus serves as a tool to cope with what would otherwise be an information avalanche. In this work, we present Social Web Application for Team Recommendation, a general‐purpose framework to compose various information retrieval and social graph mining and visualization subsystems together to build a composite team recommendation system, and instantiate it for a case study of academic teams.