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: A system and method for automatically generating deep neural network architectures for time series prediction. The system includes a processor for: receiving a prediction context associated with a current use case; based on the associated prediction context, selecting a prediction model network configured for a current use case time series prediction task; replicating the selected prediction model network to create a plurality of candidate prediction model networks; inputting a time series data to each of the plurality of the candidate prediction model network; train, in parallel, each respective candidate prediction model network of the plurality with the input time series data; modifying each of the plurality of the candidate prediction model network by applying a respective different set of one or more model parameters while being trained in parallel; and determine a fittest modified prediction model network for solving the current use case time series prediction task.

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: One or more hardened machine learning models are secured against adversarial attacks by adding adversarial protection to one or more previously trained machine learning models. To generate the hardened machine learning models, the previously trained machine learning models are retrained and extended using preprocessing layers or using additional network layers which test model performance on benign or adversarial samples. A rollback strategy is additionally implemented to retain intermediate model states during the retraining to provide recovery if a training collapse is detected.

Abstract: A method for generating a summary text composition can include obtaining historical reading data of a user. The method can include generating, based on the historical reading data, a reading proficiency level of the user. The method can include selecting, based on the reading proficiency level, a summarization model from a set of summarization models. The method can include obtaining a target composition. The target composition can be selected from the group consisting of a literary work, a video recording, and an audio recording. The method can include generating, by the summarization model, the summary text composition. The summary text composition can correspond to the target composition and have a first reading level classification that matches the reading proficiency level. The method can include transmitting the summary text composition to a computing device.

Abstract: Aspects of the present invention disclose a method for generating speech recommendations for a user based on feedback data corresponding to a plurality of viewers of the user. The method includes one or more processors identifying speech of a user in audio data of the user. The method further includes identifying feedback of one or more audience members of the user associated with the speech of the user. The method further includes generating an assessment of the speech of the user, wherein the assessment is based at least in part on the feedback of the one or more audience members. The method further includes generating a speech recommendation for the speech of the user based at least in part on the assessment of the speech.

Abstract: In an approach for discourse-level text optimization, a processor receives an initial text in a first language. A processor applies one or more operators to modify the initial text. A processor evaluates the modified text using a scoring function. A processor determines whether a score generated from the scoring function on the modified text is above a predefined threshold. In response to determining the score is above the predefined threshold, a processor outputs the modified text.

Abstract: Various embodiments are provided for automated evaluation of machine learning models in a computing environment by one or more processors in a computing system. A level of robustness of a machine learning model against adversarial whitebox operations may be evaluated and determined by applying a data set used for testing the machine learning model, one or more adversarial operation objectives, an adversarial threat model, and a selected number of hyperparameters. Results from the adversarial operation may be analyzed and a modified machine learning model may be generated while performing the evaluating and determining.

Abstract: Embodiments for providing adversarial protection to computing display devices by a processor. Security defenses may be provided on one or more image display devices against automated media analysis by using adversarial noise, an adversarial patch, or a combination thereof.

Abstract: A method for generating a summary text composition can include obtaining historical reading data of a user. The method can include generating, based on the historical reading data, a reading proficiency level of the user. The method can include selecting, based on the reading proficiency level, a summarization model from a set of summarization models. The method can include obtaining a target composition. The target composition can be selected from the group consisting of a literary work, a video recording, and an audio recording. The method can include generating, by the summarization model, the summary text composition. The summary text composition can correspond to the target composition and have a first reading level classification that matches the reading proficiency level. The method can include transmitting the summary text composition to a computing device.

Abstract: Techniques and systems for facilitating artificial intelligence for interactive preparation of electronic documents are provided. In one example, a system includes a mapping component and a document editing component. The mapping component maps data provided by a recording device into an editing action for an electronic document. The document editing component applies the editing action associated with the recording device to the electronic document to generate a modified version of the electronic document.

Abstract: Techniques facilitating iterative widening search for designing chemical compounds are provided. A computer-implemented method can comprise receiving, by a system operatively coupled to a processor, an indication of a constrained structure portion of a chemical compound and a first unconstrained structure portion of the chemical compound. The method can also comprise determining, by the system, a second unconstrained structure portion for the chemical compound based on a determination that the second unconstrained structure portion satisfies a defined condition related to a difference between the first unconstrained structure portion and the second unconstrained structure portion.

Abstract: Various embodiments are provided for automating decision making for a neural architecture search by one or more processors in a computing system. One or more specifications may be automatically selected for a dataset, tasks, and one or more constraints for a neural architecture search. The neural architecture search may be performed based on the one or more specifications. A deep learning model may be suggested, predicted, and/or configured for the dataset, the tasks, and the one or more constraints based on the neural architecture search.

Abstract: A system and method for reaction rules database correction. The method includes receiving a user-input correction to a first reaction rule in a reaction rules database, and locating a second reaction rule in the reaction rules database that is similar to the first reaction rule. The method also includes calculating a correctness score for the second reaction rule, and determining that the correctness score for the second reaction rule is below a threshold correctness score. Additionally, the method includes presenting, in response to the determining that the correctness score for the second reaction rule is below the threshold correctness score, the second reaction rule to a user, receiving a user-input correction to the second reaction rule, and updating the reaction rules database to include the user-input correction to the second reaction rule.

Abstract: Embodiments for using an intelligent transaction optimization assistant by a processor. One or more actions to enhance a transaction experience of one or more users may be provided according to one or more selected constraints learned via a machine learning operation from previous transaction experiences, user behavior relating to the one or more previous transaction experiences, transaction experiences shared amongst entities associated with a social network, or a combination thereof.

Abstract: Embodiments for optimizing seating space in a group seating arrangement by a processor. One or more seating preferences and constraints from a user may be received. An optimized seating arrangement in the group seating arrangement, having one or more adjustable seats, may be determined according to the one or more seating preferences and constraints. A user is enabled to select the optimized seating arrangement via a graphical user interface (GUI) such that the one or more adjustable seats in the group seating arrangement are dynamically adjusted according to the optimized seating arrangement and user selection.

Abstract: A method and system for generating a map identifying the size and location of anomalous crop health patterns of a geographic area. Predictive crop health forecasting based historical crop health images generates expected crop health images. Statistical parametric mapping is used to model differences in the expected crop health images and current crop health images to generate a statistical parametric map. Regions of anomalous crop health based on the modeled differences are identified in the statistical parametric map. The number of the identified anomalous crop health regions and the size of each of the identified anomalous crop health regions are determined. The statistical significance of the size and number of the anomalous crop health regions relative to the expected crop health is quantified. A map of anomalous crop health patterns delineates the anomalous crop health regions and the statistical significance of the size and number of anomalous crop health regions.

Abstract: Embodiments describe an approach for coordinating the travel of multiple vehicles traveling to a target destination, the embodiments describe generating a travel group, receiving travel group parameters from travel group members, synced GPS applications, and a weather application, generating a course of travel for the travel group members to reach a destination, and tracking each travel group member according to locations identified by the synced GPS applications. Additionally, embodiments describe determining that a subgroup of the travel group is no longer traveling within a pre-determined range of other travel group members; calculating an optimized course of travel for the subgroup to reunite with the other travel group members, adjusting the course of travel to include the optimized course of action for the subgroup, and causing each GPS application to direct the subgroup to travel according to the optimized course of travel.

Abstract: Embodiments for providing adversarial protection to computing display devices by a processor. Security defenses may be provided on one or more image display devices against automated media analysis by using adversarial noise, an adversarial patch, or a combination thereof.

Abstract: Various embodiments are provided for securing trained machine learning models by one or more processors in a computing system. One or more hardened machine learning models are secured against adversarial attacks by adding adversarial protection to one or more trained machine learning model.