Abstract: An example computer system for providing countermeasures for a ransomware attack can include: one or more processors; and non-transitory computer-readable storage media encoding instructions which, when executed by the one or more processors, causes the computer system to generate a key by to: create a salt using artificial intelligence; form a data section by the salt and an original key; and form a dummy section to fill out a length of the key.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for automated model development. An example method includes parsing, by configuration circuitry, a configuration file, and generating, by an execution engine and based on the parsed configuration file, model code for training and testing a machine learning model. The example method further includes generating, by the execution engine, a machine learning pipeline, wherein the machine learning pipeline comprises the model code and a data processing engine, and instantiating, by a monitoring driver, a monitoring engine to monitor the machine learning pipeline. The example method further includes causing execution, by the execution engine, of the machine learning pipeline, and during execution of the machine learning pipeline, generating model performance data by the monitoring engine.

Abstract: A method may include receiving, using a processing unit, a prompt for a generative artificial intelligence model from a computing device; identifying, using the processing unit, an entity in the prompt; querying a knowledge graph for verified information associated with the entity; inputting, using the processing unit, the prompt into the generative artificial intelligence model; in response to the inputting, receiving a generated response from the generative artificial intelligence model; generating a similarity value between the generated response and the verified information; determining that the similarity value is below a threshold similarity; and based on the determining, preventing a display of the generated response.

Abstract: An example computer system for providing countermeasures for a ransomware attack can include: one or more processors; and non-transitory computer-readable storage media encoding instructions which, when executed by the one or more processors, causes the computer system to: recommend one or more countermeasures once the ransomware attack is identified; switch access for a client device from an application layer to a software defined network layer including a software defined network trap having nodes; and restrict access when the client device fails to perform a task at a node of the software defined network trap.

Abstract: An example computer system for providing countermeasures for a ransomware attack can include: one or more processors; and non-transitory computer-readable storage media encoding instructions which, when executed by the one or more processors, causes the computer system to generate a key by to: create a salt using artificial intelligence; form a data section by the salt and an original key; and form a dummy section to fill out a length of the key.

Abstract: Systems and methods are provided, that include receiving a request from a requestor for an artificial intelligence (AI)-generated output, and determining an intended audience for the AI-generated output based on the request. The systems and methods also creating an audience-based response to the request by using a trained large language model (LLM) or a combination of the trained LLM and an LLM style-based embedding. Using the trained LLM includes generating a base response to the request using the trained LLM, and applying one or more audience-specific transformation systems to the base response to create the audience-based response, wherein the one or more audience-specific transformation systems are configured to modify the base response for the intended audience. The systems and methods additionally include providing the audience-based response as the AI-generated output to the requestor.

Abstract: Systems and techniques to increase generative artificial intelligence accountability and explainability using information gates are described herein. A prompt directed to a generative artificial intelligence (AI) model is obtained and a group of input sets in a repository, and a set operation, are identified from the prompt. This set operation is applied to a first input set and a second input set to produce an inclusion filter. The inclusion filter specifies which data from the group of input sets is included in an intermediate set. The generative AI model is then invoked on this intermediate set to produce a result.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for automated model development. An example method includes parsing, by configuration circuitry, a configuration file, and generating, by an execution engine and based on the parsed configuration file, model code for training and testing a machine learning model. The example method further includes generating, by the execution engine, a machine learning pipeline, wherein the machine learning pipeline comprises the model code and a data processing engine, and instantiating, by a monitoring driver, a monitoring engine to monitor the machine learning pipeline. The example method further includes causing execution, by the execution engine, of the machine learning pipeline, and during execution of the machine learning pipeline, generating model performance data by the monitoring engine.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for compiling AI system outputs into unified responses. An example method includes receiving response data that is representative of one or more AI system outputs. The example method further includes identifying a task request associated with the response data. The example method further includes generating a unified response associated with the task request. The example method further includes causing transmission of the unified response to a user device associated with the task request. The example method may further include determining an AI system server that transmitted the response data.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for routing task request to one or more AI systems. An example method includes receiving a subtask request that is representative of instructions to execute an actionable subtask. The example method further includes determining computational capabilities associated with one or more AI systems. The example method further includes matching the subtask request with a target AI system of the one or more AI systems. The example method further includes causing transmission of the subtask request to the target AI system. The example method may further include determining an intelligent or optimized routing for the subtask request based on the computational capabilities of the one or more AI systems and the particular content or type of a subtask request.

Abstract: A computing system may be configured for generating a source-based confidence score in association with output from a Large Language Model (LLM). The computing system may obtain computer-generated text output from the LLM as an answer to an inquiry submitted by a computing device. The computing system may determine a confidence score in association with the answer to the inquiry based on an evaluation of one or more sources used by the LLM to generate the answer and determine whether the confidence score associated with the answer satisfies a quality threshold. Based on the confidence score associated with the answer satisfying the quality threshold, the computing system may generate an annotated answer including the answer and an indication of quality based on the evaluation of the one or more sources used by the LLM to generate the answer. The annotated answer may be output in response to the inquiry.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for automated model development. An example method includes parsing, by configuration circuitry, a configuration file, and generating, by an execution engine and based on the parsed configuration file, model code for training and testing a machine learning model. The example method further includes generating, by the execution engine, a machine learning pipeline, wherein the machine learning pipeline comprises the model code and a data processing engine, and instantiating, by a monitoring driver, a monitoring engine to monitor the machine learning pipeline. The example method further includes causing execution, by the execution engine, of the machine learning pipeline, and during execution of the machine learning pipeline, generating model performance data by the monitoring engine.