Abstract: Adversarial attack detection operations may be applied on one or more deep generative models for defending deep generative models from adversarial attacks. The adversarial attack may be detected on the one or more deep generative models based on the one or more of a plurality of adversarial attack detection operations. The one or more deep generative models may be sanitized based on the adversarial attack.

Abstract: Protection against prying devices on a computer network is provided. The method comprises identifying a number of prying devices connected to the computer network, wherein the prying devices have the capability to record audio and/or video data, and wherein the prying devices have the potential to eavesdrop on an audio/video conference call. Responsive to detecting initiation of the audio/video conference call, the prying devices are prevented from communicating over the computer network. Responsive to detecting termination of the audio/video conference call, the prying devices are allowed to resume communication over the computer network.

Abstract: A method, computer system, and computer program product are provided for training a federated generative adversarial network (GAN) using private data. The method is carried out at an aggregator system having a generator and a discriminator, wherein the aggregator system is in communication with multiple participant systems each having a local feature extractor and a local discriminator. The method includes: receiving, from a feature extractor at a participant system, a set of features for input to the discriminator at the aggregator system, wherein the features include features extracted from private data that is private to the participant system; and receiving, from one or more local discriminators of the participant systems, discriminator parameter updates to update the discriminator at the aggregator system, wherein the local discriminators are trained at the participant systems.

Abstract: A system may receive inputs including a media, a targeted object keyword list, and a command. The system may feed expanded targeted object keywords into an object detector selector. The system may determine a target object area in the media, by the object detector selector using one or more object detector models. The system may feed the media, and the target object area into an area filler module. The system may generate a background, the area filler module in a target object area of the media.

Abstract: A method, computer system, and a computer program product for data processing, comprising obtaining a plurality of files from a data source. These files are analyzed the files for information about the content and in order to determine structural information of each file. Once the files have been analyzed, information in each file may be sorted and categorized by common content. Sensitive information may also be extracted and categorized separately. Information may then be then merged using the categories to create a single unified file.

Abstract: Predetermined musical data for a song is received. The predetermined musical data includes chords and lyrics and rhythmic structures of the song. Audio data of a band generating music of the song is received. Generating real-time vocal audio that is in rhythm with the audio data and in harmony with the chords. The vocal audio includes the lyrics and is of a predetermined voice.

Abstract: Embodiments for ensemble training in a distributed marketplace in a computing environment. One or more ensemble machine learning models may be provided from a plurality of machine learning models competing within the distributed marketplace that achieve a performance on ensemble training data equal to or greater than a selected performance threshold, wherein the distributed marketplace is a blockchain.

Abstract: A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include procuring a model and obtaining hyperparameters for watermarking the model. The operations may include embedding a watermark in the model using the hyperparameters to achieve a watermarked model and delivering the watermarked model and a watermark verification mechanism to a user.

Abstract: Embodiments of the invention are directed to techniques that include receiving a query intended for a targeted database and determining that the query is from an unauthorized user. A response is returned to the unauthorized user generated by a model, the response being dynamically generated to fulfill the query. The model is configured to generate responses consistent with any previous responses returned to the unauthorized user.

Abstract: A method, computer program, and computer system are provided for predicting and assessing risks on websites. Data corresponding to historical interactions of a user with one or more websites is accessed. A simulation of actions of the user is generated based on the accessed data, and actions of the user are simulated on a pre-defined target website based on the generated simulation of the actions of the user. Risks on the target website are identified based on simulating the actions of the user. The website is updated to mitigate the identified risks.

Abstract: A computer-implemented method, a computer program product, and a computer system for assessing fairness of a deep generative model. A computer system receives a user defined fairness criterion for the deep generative model. A computer system probes the deep generative model to produce samples for a target output. A computer system evaluates the samples for the fairness of the deep generative model, according to the user defined fairness criterion. A computer system produces a set of recommendations for modifying the deep generative model to meet the user defined fairness criterion, in response to determining that the deep generative model does not meet the user defined fairness criterion. In response to determining that the deep generative model is to be modified, a computer system applies at least one subset of the recommendations to the deep generative model. A computer system updates the deep generative model.

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to facilitating a process to compensate a service being provided over a network connection. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise a determination component that determines a network connection between a server and a client node, and a predictive component that predicts, employing machine learning, a graphical representation update to a service provided by the server over the network connection. The predictive component can generate the prediction in response to a decrease in bandwidth and/or an increase in latency of a network connection. A training component can train a machine learning model employed by the predictive component based on historical data of the service provided by the server.

Abstract: Adversarial attack detection operations may be applied on one or more deep generative models for defending deep generative models from adversarial attacks. The adversarial attack may be detected on the one or more deep generative models based on the one or more of a plurality of adversarial attack detection operations. The one or more deep generative models may be sanitized based on the adversarial attack.

Abstract: A method, computer system, and a computer program product for text data protection is provided. The present invention may include receiving a text data. The present invention may also include identifying a portion of the received text data having a highest impact on a first confidence score associated with a target model prediction. The present invention may further include generating at least one semantically equivalent text relative to the identified portion of the received text data. The present invention may also include determining that the generated at least one semantically equivalent text produces a second confidence score associated with the target model prediction that is less than the first confidence score associated with the target model prediction. The present invention may further include generating a prompt to suggest modifying the identified portion of the received text data using the generated at least one semantically equivalent text.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate sensitive data policy recommendation are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an extraction component that can employ an artificial intelligence model to extract compliance data from a data source. The computer executable components can further comprise a recommendation component that can recommend a sensitive data policy based on the compliance data. In some embodiments, the recommendation component can further identify one or more sensitive data entities of a sensitive data dataset that are affected by actionable obligation data of the data source.

Abstract: Various embodiments are provided for managing regulatory compliance for an entity in a computing environment by a processor. A law, policy, regulation, or a combination thereof extracted from one or more segments of text data from one or more data sources may be identified requiring an obligation to be performed by the entity.

Abstract: Embodiments include a method for one or more processors to receive an organic dataset and a domain knowledge base. The one or more processors identify private data entities present within the organic dataset. The one or more processors determine statistical properties of the private data entities identified within the organic dataset. The one or more processors create a plurality of test data templates by removing the private data entities from the organic dataset. The one or more processors select from the domain knowledge base, synthetic data entities that match a data type of the removed private data entities, respectively, and align with the statistical properties of the private data entities, and the one or more processors generate synthetic test data by inserting, respectively, the synthetic data entities of the matching data type for the removed private data entities in the test data templates.

Abstract: A computer-implemented method includes receiving at a threat detection system monitoring data in real-time from online activity in a network, the threat detection system including a machine learning model, and analyzing the monitoring data via the machine learning model to identify one or more anomalies in the monitoring data associated with a security threat to the network, the machine learning model trained to have one or more learning parameters. The method also includes receiving a subset of the monitoring data at a meta-learning module, storing the subset as time-based historical data, inputting the historical data at a meta-learning model, calculating an update policy prescribing a change to the one or more learning parameters based on the historical data, and applying the update policy to the machine learning model.

Abstract: Methods, systems and computer program products for protection of content repositories using dynamic watermarking are provided. Aspects include receiving a request for a code stored in a content repository from a user and identifying a plurality of candidate locations in the code to insert watermarks. Aspects also include generating one or more watermarks and inserting the one or more watermarks in a subset of the plurality of candidate locations in the code. Aspects further include providing the code, including the one or more watermarks, to the user.

Abstract: Methods, systems and computer program products for protection of content repositories using dynamic watermarking are provided. Aspects include receiving a request for a code stored in a content repository from a user and identifying a plurality of candidate locations in the code to insert watermarks. Aspects also include generating one or more watermarks and inserting the one or more watermarks in a subset of the plurality of candidate locations in the code. Aspects further include providing the code, including the one or more watermarks, to the user.