The present invention provides a method for adaptive network intrusion detection that includes: a) deploying a network traffic capture system and collecting network packet traces; b) using a network audit tool (122) to extract features from the collected network packet traces; c) feeding the extracted features as unlabeled data (U) into a representation function and utilizing the representation function as an unsupervised feature learning algorithm (132) to learn a new representation of the unlabeled data (U); d) providing a labeled training set (T) capturing examples of malicious network traffic and using the learned new representation of the unlabeled data (U) to modify the labeled training set (T) to obtain a new training set (formula (I)); and e) using the new training set (formula (I)) to train a traffic classification machine learning model. Furthermore, the present invention provides a respective system for adaptive network intrusion detection.
A detection rules generation engine includes an initial population creation subsystem configured to receive filtered network traffic instances from a network tap and to build an initial population of decision trees having nodes which are sorted based on an information gain of network features of the traffic instances. A parents selection subsystem is configured to select two individuals from the population based on a selection probability. A depth selection subsystem is configured to select a depth among the nodes of the decision trees. A parents crossover subsystem is configured to apply a crossover operation on the selected individuals. A parents mutation subsystem is configured to apply a mutation operation on the selected individuals. A population replacement subsystem is configured to generate a next population.
A method coordinating home services is provided, including receiving a request for home services from a customer over a network and forwarding the request from the customer to a home services coordinator over the network. A reputation system assists the home services coordinator to select a service provider based on customer needs, preferences, and a reputation of the service provider. Information sufficient to permit the service provider to select a home delivery provider that can satisfy customer needs is provided to the selected service provider over the network. The selected home delivery provider is provided with access to customer data and with access to a customer physical system over the network, to provide the service. Feedback is requested from the customer after the service has been delivered, and is used in the reputation system to update the customer preferences and the reputation of the service provider.
The present invention relates to a system for determining a reputation mechanism, wherein at least two reputation engines are each operable to determine a reputation score of a system entity according to a reputation mechanism, a selection entity for selecting one of the at least two reputation engines, a condition entity for measuring a condition of the system according to at least one system condition parameter and for providing corresponding condition information, a performance entity for measuring a performance of the system according to at least one system performance parameter, and for providing corresponding performance information, wherein the selection entity is operable to select a reputation engine out of the at least two reputation engines based on actual provided condition information and/or actual provided performance information. The present invention relates also to a corresponding method.
A method for performing single sign-in user authentication, comprising a number of relying parties (3) that offer particular services, users (2) being enabled to request access to a service offered by a relying party (3), and a number of authentication entities performing authentication of a user’s (2) identity towards a relying party (3), is characterized in that said authentication entities provide a user (2), within the framework of an authentication process towards a relying party (3), with reputation information about said relying party (3). Furthermore, a corresponding system is described.
A method for operating a smart grid including a plurality of smart meters, said smart meters being configured to monitor at least one physical measured quantity and to provide measurement results of said at least one physical measured quantity to a central entity, is characterized in the following steps: said smart grid is partitioned into groups G of smart meters sm i , such that each of said smart meters belongs to exactly one group, all smart meters sm i of one of said groups G encrypt their measured value e i by applying a bihomomorphic encryption scheme E ki and send it to said central entity, one smart meter per group is designated as key aggregator to which all smart meters sm i of that group send their key k i employed for said encryption, said key aggregator computes the aggregation of all received keys k i and sends the aggregated key K to said central entity, said central entity aggregates all received encrypted measured values e i and decrypts said aggregation by employing said aggregated key K. Furthermore, a corresponding smart grid is disclosed.
A method for supporting a reputation mechanism in a network, wherein said network includes one or more domains with one or more users being connected to said domains, one or more Identity Providers that manage identity information on behalf of said users, and at least one entity that functions as Web Service Consumer for said users, is characterized in that, in case a user requests a Web Service Consumer of one of said domains for a web service provided by a Web Service Provider, in particular of another of said domains, said requested Web Service Consumer requests its known Identity Providers regarding a recommendation of said Web Service Provider, wherein said Identity Providers function as recommendation aggregators by collecting reputation assessments of said Web Service Provider from entities being registered on said Identity Providers, in particular users and/or Web Service Consumers, wherein said Identity Providers return an aggregated recommendation to said requested Web Service Consumer that, on the basis of said aggregated recommendation, determines a trust assessment about said Web Service Provider, and wherein a privacy homomorphism is employed for providing an encrypted exchange of recommendation related information between said Identity Providers and said requested Web Service Consumer. Furthermore, a corresponding network including a reputation mechanism is disclosed.
Félix Gómez Mármol, Javier Pastor Galindo, Enrique T. Martínez Beltrán, Mario Quiles Pérz, Pantaleone Nespoli, Félix J. García Clemente, «ConVIDa: COVID19 data monitoring in Spain«, University of Murcia, 18/05/2020