Abstract: Techniques regarding privacy preservation in a federated learning environment are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a plurality of machine learning components that can execute a machine learning algorithm to generate a plurality of model parameters. The computer executable components can also comprise an aggregator component that can synthesize a machine learning model based on an aggregate of the plurality of model parameters. The aggregator component can communicate with the plurality of machine learning components via a data privacy scheme that comprises a privacy process and a homomorphic encryption process in a federated learning environment.

Abstract: A computer-implemented method includes receiving characteristics of available resources usable for downloading layers of a container image and fetching a manifest of the container image from a container registry. The method includes determining layers of the container image to be downloaded based on the manifest and, based on the characteristics of the available resources and sizes of the layers to be downloaded, adjusting an optimal parallelism to download the layers. The method includes downloading the layers.

Abstract: One embodiment provides a method comprising intercepting an incoming communication for a user, and determining whether to classify the incoming communication as a suspicious incoming communication based on content of the incoming communication and a learned classification model or learned signatures. The method further comprises monitoring one or more outgoing communications from the user, and invoking an action relating to scam prevention in response to determining an outgoing communication from the user is linked to a suspicious incoming communication.

Abstract: One embodiment provides a method comprising intercepting a voice communication, collecting multi-sensory inputs associated with the voice communication, and determining an overall risk assessment metric for the voice communication based on the multi-sensory inputs and learned signatures. The multi-sensory inputs are indicative of content of the voice communication and one or more contextual factors associated with a target of the voice communication. The overall risk assessment metric indicates a likelihood the voice communication is a scam.

Abstract: One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data.

Abstract: One embodiment provides a method comprising intercepting an incoming communication for a user, and determining whether to classify the incoming communication as a suspicious incoming communication based on content of the incoming communication and a learned classification model or learned signatures. The method further comprises monitoring one or more outgoing communications from the user, and invoking an action relating to scam prevention in response to determining an outgoing communication from the user is linked to a suspicious incoming communication.

Abstract: One embodiment provides a method for monitoring context-dependent quality of service in a shared computing environment that includes detecting, by a processor, a change in context. Context includes user context and external context, and user context comprises physical activity, mood, engagement levels and type of events. Prior assigned service classes are updated to updated service classes based on the change in context. Service level agreement (SLA) statistics for each assigned service class are aggregated and collected. Each assigned service class includes at least one SLA based on aggregate services received by individual users in that assigned service class, and aggregating SLA statistics is based on a statistical function.

Abstract: One embodiment provides a method for monitoring context-dependent quality of service in a shared computing environment that includes detecting, by a processor, a change in context. Service classes are dynamically assigned to individual users and respective applications within shared computing environment customers based on the change in context. Service level agreement (SLA) statistics for each assigned service class are aggregated and collected.

Abstract: One embodiment provides a method comprising receiving a request to release a utility holder detachably mounted to a surface mount. The utility holder maintains a utility payload. A set of rotatable holding brackets is coupled to the surface mount in a pivotable fashion to engage the holding brackets with the utility holder in order to mount the utility holder to the surface mount. The method further comprises, in response to receiving the request, powering on a drone attached to the utility holder, and releasing the utility holder from the surface mount by actuating rotation of the holding brackets to disengage the holding brackets from the utility holder, enabling the drone to transport the utility holder from the surface mount to a desired location.

Abstract: One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data.

Abstract: A computer-implemented method according to one embodiment includes identifying a topic associated with a received notification, determining a plurality of policies associated with the topic, determining a current environmental context, determining a generalization level, utilizing the plurality of policies and the current environmental context, modifying the notification, based on the generalization level, and presenting the modified notification.

Abstract: A computer-implemented method includes identifying a plurality of protected pieces from a conversation. The computer-implemented method further includes generating one or more confidence scores for each protected piece, wherein a confidence score is a degree of associativity between a protected piece and a type of sensitive information. The computer-implemented method further includes determining that the protected piece is associated with the type of sensitive information. The computer-implemented method further includes determining a type of protection action for each protected piece in the plurality of protected pieces. The computer-implemented method further includes performing the type of protection action for each protected piece in the plurality of protected pieces to form a modified conversation that is devoid of the sensitive information. A corresponding computer system and computer program product are also disclosed.

Abstract: One embodiment provides a method comprising receiving a training set comprising a plurality of data points, where a neural network is trained as a classifier based on the training set. The method further comprises, for each data point of the training set, classifying the data point with one of a plurality of classification labels using the trained neural network, and recording neuronal activations of a portion of the trained neural network in response to the data point. The method further comprises, for each classification label that a portion of the training set has been classified with, clustering a portion of all recorded neuronal activations that are in response to the portion of the training set, and detecting one or more poisonous data points in the portion of the training set based on the clustering.

Abstract: One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data.

Abstract: A computer-implemented method includes identifying a plurality of protected pieces from a conversation. The computer-implemented method further includes generating one or more confidence scores for each protected piece, wherein a confidence score is a degree of associativity between a protected piece and a type of sensitive information. The computer-implemented method further includes determining that the protected piece is associated with the type of sensitive information. The computer-implemented method further includes determining a type of protection action for each protected piece in the plurality of protected pieces. The computer-implemented method further includes performing the type of protection action for each protected piece in the plurality of protected pieces to form a modified conversation that is devoid of the sensitive information. A corresponding computer system and computer program product are also disclosed.

Abstract: Computer-implemented methods, program products, and systems for provenance-based defense against poison attacks are disclosed. In one approach, a method includes: receiving observations and corresponding provenance data from data sources; determining whether the observations are poisoned based on the corresponding provenance data; and removing the poisoned observation(s) from a final training dataset used to train a final prediction model. Another implementation involves provenance-based defense against poison attacks in a fully untrusted data environment. Untrusted data points are grouped according to provenance signature, and the groups are used to train learning algorithms and generate complete and filtered prediction models. The results of applying the prediction models to an evaluation dataset are compared, and poisoned data points identified where the performance of the filtered prediction model exceeds the performance of the complete prediction model.

Abstract: One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data.

Abstract: One embodiment provides a method comprising answering one or more incoming phone calls received at one or more pre-specified phone numbers utilizing a bot. The bot is configured to engage in a conversation with a caller initiating an incoming phone call utilizing a voice recording that impersonates a human being. The method further comprises recording each conversation the bot engages in, and classifying each recorded conversation as one of poison data or truthful training data based on content of the recorded conversation and one or more learned detection models for detecting poisoned data.

Abstract: In one embodiment, a computer program product includes a computer-readable storage medium having program instructions embodied therewith. The embodied program instructions are executable by a processor to cause the processor to receive, by the processor, a first job request. The embodied program instructions are also executable by the processor to cause the processor to analyze, by the processor, the first job request to determine a user skill level of a user that submitted the first job request. Moreover, the embodied program instructions are executable by the processor to cause the processor to admit, by the processor, the first job request to a data analytics system and/or a data storage system in a specified order with respect to other received job requests based on at least the user skill level of the user that submitted the first job request. Other systems and methods are described in accordance with more embodiments.

Abstract: According to one embodiment, a method, computer system, and computer program product for preventing statistical inference attacks is provided. The present invention may include splitting records into items, and classifying these items into shared items and private items; grouping the private items according to privacy and confidentiality requirements; restricting access of the private items to stakeholders based on the confidentiality requirements using cryptographic keys; generating and encrypting one or more placeholders for both existent and non-existent stakeholders; storing private items in private storage as indicated by links; creating shared records comprising links, placeholders, and shared items; adding integrity signatures to the shared records; and publishing the shared records to a shared medium.