Biblio

Homomorphic Encryption is one of the most promising techniques to deal with privacy concerns, which is raised by remote deep learning paradigm, and maintain high classification accuracy. However, homomorphic encryption-based solutions are characterized by high overhead in terms of both computation and communication, which limits their adoption in pervasive health monitoring applications with constrained client-side devices. In this paper, we propose PReDIHERO, an improved privacy-preserving solution for remote deep learning inferences based on homomorphic encryption. The proposed solution applies a reversible obfuscation technique that successfully protects sensitive information, and enhances the client-side overhead compared to the conventional homomorphic encryption approach. The solution tackles three main heavyweight client-side tasks, namely, encryption and transmission of private data, refreshing encrypted data, and outsourcing computation of activation functions. The efficiency of the client-side is evaluated on a healthcare dataset and compared to a conventional homomorphic encryption approach. The evaluation results show that PReDIHERO requires increasingly less time and storage in comparison to conventional solutions when inferences are requested. At two hundreds inferences, the improvement ratio could reach more than 30 times in terms of computation overhead, and more than 8 times in terms of communication overhead. The same behavior is observed in sequential data and batch inferences, as we record an improvement ratio of more than 100 times in terms of computation overhead, and more than 20 times in terms of communication overhead.

The pervasiveness of personalized collaborative recommender systems has shown the powerful capability in a wide range of E-commerce services such as Amazon, TripAdvisor, Yelp, etc. However, fundamental vulnerabilities of collaborative recommender systems leave space for malicious users to affect the recommendation results as the attackers desire. A vast majority of existing detection methods assume certain properties of malicious attacks are given in advance. In reality, improving the detection performance is usually constrained due to the challenging issues: (a) various types of malicious attacks coexist, (b) limited representations of malicious attack behaviors, and (c) practical evidences for exploring and spotting anomalies on real-world data are scarce. In this paper, we investigate a unified detection framework in an eye for an eye manner without being bothered by the details of the attacks. Firstly, co-visitation and co-rating graphs are constructed using association rules. Then, attribute representations of nodes are empirically developed from the perspectives of linkage pattern, structure-based property and inherent association of nodes. Finally, both attribute information and connective coherence of graph are combined in order to infer suspicious nodes. Extensive experiments on both synthetic and real-world data demonstrate the effectiveness of the proposed detection approach compared with competing benchmarks. Additionally, abnormality forensics metrics including distribution of rating intention, time aggregation of suspicious ratings, degree distributions before as well as after removing suspicious nodes and time series analysis of historical ratings, are provided so as to discover interesting findings such as suspicious nodes (items or ratings) on real-world data.

State-of-the-art security frameworks have been extensively addressing security issues for web resources, agents and services in the Semantic Web. The provision of Stream Reasoning as a new area spanning Semantic Web and Data Stream Management Systems has eventually opened up new challenges. Namely, their decentralized nature, the metadata descriptions, the number of users, agents, and services, makes securing Stream Reasoning systems difficult to handle. Thus, there is an inherent need of developing new security models which will handle security and automate security mechanism to a more autonomous system that supports complex and dynamic relationships between data, clients and service providers. We plan to validate our proposed security model on a typical application of stream data, on Wireless Sensor Networks (WSNs). In particular, WSNs for water quality monitoring will serve as a case study. The proposed model can be a guide when deploying and maintaining WSNs in different contexts. Moreover, this model will point out main segments which are most important in ensuring security in semantic stream reasoning systems, and their interrelationships. In this paper we propose a security framework to handle most important issues of security within WSN. The security model in itself should be an incentive for other researchers in creating other models to improve information security within semantic stream reasoning systems.

Machine learning (ML) models are often trained using private datasets that are very expensive to collect, or highly sensitive, using large amounts of computing power. The models are commonly exposed either through online APIs, or used in hardware devices deployed in the field or given to the end users. This provides an incentive for adversaries to steal these ML models as a proxy for gathering datasets. While API-based model exfiltration has been studied before, the theft and protection of machine learning models on hardware devices have not been explored as of now. In this work, we examine this important aspect of the design and deployment of ML models. We illustrate how an attacker may acquire either the model or the model architecture through memory probing, side-channels, or crafted input attacks, and propose (1) power-efficient obfuscation as an alternative to encryption, and (2) timing side-channel countermeasures.

The rapid growth in the size and scope of datasets in science and technology has created a need for novel foundational perspectives on data analysis that blend the inferential and computational sciences. That classical perspectives from these fields are not adequate to address emerging problems in "Big Data" is apparent from their sharply divergent nature at an elementary level-in computer science, the growth of the number of data points is a source of "complexity" that must be tamed via algorithms or hardware, whereas in statistics, the growth of the number of data points is a source of "simplicity" in that inferences are generally stronger and asymptotic results can be invoked. On a formal level, the gap is made evident by the lack of a role for computational concepts such as "runtime" in core statistical theory and the lack of a role for statistical concepts such as "risk" in core computational theory. I present several research vignettes aimed at bridging computation and statistics, including the problem of inference under privacy and communication constraints, and ways to exploit parallelism so as to trade off the speed and accuracy of inference.

Semantic Big Data is about the creation of new applications exploiting the richness and flexibility of declarative semantics combined with scalable and highly distributed data management systems. In this work, we present an application scenario in which a domain ontology, Open Refine and the Okkam Entity Name System enable a frictionless and scalable data integration process leading to a knowledge base for tax assessment. Further, we introduce the concept of Entiton as a flexible and efficient data model suitable for large scale data inference and analytic tasks. We successfully tested our data processing pipeline on a real world dataset, supporting ACI Informatica in the investigation for Vehicle Excise Duty (VED) evasion in Aosta Valley region (Italy). Besides useful business intelligence indicators, we implemented a distributed temporal inference engine to unveil VED evasion and circulation ban violations. The results of the integration are presented to the tax agents in a powerful Siren Solution KiBi dashboard, enabling seamless data exploration and business intelligence.