Abstract: Systems, methods, and software for analyzing data logs. In one embodiment, a method comprises collecting a plurality of the data logs from log-generating elements, converting the data logs into log images, performing image analysis on a plurality of the log images to extract insights, and generating an output based on the insights.

Abstract: Techniques for security management with compromised-equipment detection in a communication system are disclosed. For example, a method comprises causing intentional introduction of one or more errors in at least one communication protocol layer of a communication network, wherein the communication network has a plurality of user equipment connected thereto via at least one access point. The method further comprises causing verification of one or more received error indicators against one or more expected error indicators to decide whether any of: (i) the plurality of user equipment; (ii) the at least one access point; or (iii) one or more network entities, may be compromised. In other examples, verifications may be correlated with other logs including, for example, security event logs.

Abstract: There are provided measures for improved robustness of artificial intelligence or machine learning capabilities against compromised input. Such measures exemplarily comprise receiving, from a first machine learning model training data collection entity, first machine learning model training input data, analyzing said first machine learning model training input data for malicious input detection, deducing, based on a result of said analyzing, whether said first machine learning model training data collection entity is suspected to be compromised, and transmitting, if said first machine learning model training data collection entity is suspected to be compromised, information to a core network entity indicative of that said first machine learning model training data collection entity is suspected to be compromised.

Abstract: Embodiments of the present disclosure relate to a method, device, apparatus and computer readable medium for certificate updates. According to embodiments of the present disclosure, a first device receives information of at least one network function. The information at least comprises certificate information of the at least one network function. The first device determines a schedule for triggering certificate update for the at least one network function using an artificial intelligence/machine learning (AI/ML) model on the first device. The first device triggers a certificate update procedure for the at least one network function according to the determined schedule. In this way, it can avoid overload in the system due to bulk certificate updates happening simultaneously.

Abstract: Systems, methods, and software for analyzing data logs. In one embodiment, a method comprises collecting a plurality of the data logs from log-generating elements, converting the data logs into log images, performing image analysis on a plurality of the log images to extract insights, and generating an output based on the insights.

Abstract: A server (12) comprising means (123) for: generating at least one updated set of model parameters based on at least one current set of model parameters received from at least one apparatus (100-n), the at least one updated set of model parameters being parameters of a machine learning model and being an update of the at least one current set of model parameters; sending the at least one updated set of model parameters to at least one apparatus (100-n).

Abstract: There is provided an apparatus comprising means for receiving, at an image creation agent, a data set; generating, by the image creation agent, based on the received data set, an image associated with the data set, wherein pixel values in the image represent values of data entries of a plurality of rows of data of the data set; and outputting, from the image creation agent, the generated image.

Abstract: There is provided an apparatus configured to: receive, from a management service, location data associated with each of a plurality of transmitters; receive beam and/or antenna parameters associated with beams provided by the plurality of transmitters; use the received location data and received parameters to generate image data representing transmission ranges of the plurality of transmitters; and provide the generated image data to the management service.