Abstract: The present disclosure includes computer-implemented methods of guardrails for securely using large language models (LLMs). The method comprises monitoring user data flow using an application programming interface (API) and receiving an administrative policy from an administration communication interface. The method involves dynamically applying a plurality of LLM input inspectors to LLM input data. The application of the plurality of LLM input inspectors is based on the administration policy. The dynamic application of the plurality of LLM input inspectors is in sequence for latency optimization. The plurality of LLM input inspectors serve as LLM input guardrails for a plurality of secure deployed large language models (LLMs). The plurality of LLM input inspectors are configured by the administrative policy and validate the LLM input data to validated LLM input data based on the administration policy.

Abstract: The present technology relates to a computer-implemented method for enhancing enterprise-wide security when using Artificial Intelligence (AI) models. Embodiments involve a JavaScript injection process facilitated by a proxy server. This process does not require manual installation as it is automatically injected during operation. The JavaScript injection process operates by intercepting unsecured AI input and output data provided by users interacting with AI websites. The input and output data are sent to a security Application Programming Interface (API) which applies an enterprise security policy to the data in real time, thereby transforming unsecured input and output into secure data. Embodiments provide a robust framework for safe interaction with Artificial Intelligence models while mitigating the risks associated with the transmission of sensitive information over the internet.

Abstract: A processor may capture network packets from a communication channel between a user and an application, the network packets comprising a data structure package. A processor may identify a schema of a payload used in the data structure package of the network packets. A processor may dynamically generate payload schema processing code using a machine learning dynamic protocol parser by applying a machine learning model to the schema of the payload, the payload schema processing code including a description of each field of the data structure package and a parser function for extracting a prompt. A processor may iterate the dynamically generating of the payload schema processing code until the payload schema processing code meets a predefined accuracy and functionality criteria that successfully extracts the prompt.

Abstract: The present technology relates to a computer-implemented method for enhancing enterprise-wide security when using Artificial intelligence (AI) models. Embodiments involve a JavaScript injection process facilitated by a proxy server. This process does not require manual installation as it is automatically injected during operation. The JavaScript injection process operates by intercepting unsecured AI input and output data provided by users interacting with AI websites. The input and output data are sent to a security Application Programming Interface (API) which applies an enterprise security policy to the data in real-time, thereby transforming unsecured input and output into secure data. Embodiments provide a robust framework for safe interaction with Artificial intelligence models while mitigating the risks associated with the transmission of sensitive information over the internet.

Abstract: The present technology relates to a computer-implemented method for enhancing enterprise-wide security when using Artificial intelligence (AI) models. Embodiments involve a JavaScript injection process facilitated by a proxy server. This process does not require manual installation as it is automatically injected during operation. The JavaScript injection process operates by intercepting unsecured AI input and output data provided by users interacting with AI websites. The input and output data are sent to a security Application Programming Interface (API) which applies an enterprise security policy to the data in real-time, thereby transforming unsecured input and output into secure data. Embodiments provide a robust framework for safe interaction with Artificial intelligence models while mitigating the risks associated with the transmission of sensitive information over the internet.

Abstract: The present disclosure includes computer-implemented methods of guardrails for securely using large language models (LLMs). The method comprises monitoring user data flow using an application programming interface (API) and receiving an administrative policy from an administration communication interface. The method involves dynamically applying a plurality of LLM input inspectors to LLM input data. The application of the plurality of LLM input inspectors is based on the administration policy. The dynamic application of the plurality of LLM input inspectors is in sequence for latency optimization. The plurality of LLM input inspectors serve as LLM input guardrails for a plurality of secure deployed large language models (LLMs). The plurality of LLM input inspectors are configured by the administrative policy and validate the LLM input data to validated LLM input data based on the administration policy.