Abstract: A method for monitoring a system includes receiving a time sequence of data; determining presence or absence of an anomaly in the time sequence of data, absence of an anomaly corresponding to absence of a particular event occurring in the system and absence of an irregularity intrinsic to the time sequence of data, the determining using a machine learning model; if the presence of an anomaly has been determined, generating identification information relating to the anomaly; receiving, via the user interface, confirmation information relating to the presence or not of an anomaly in the time sequence of data; using the confirmation information and the identification information to train the machine learning model via a learning mechanism.

Abstract: A method, system, and computer program product configured to perform operations including: identifying sensitive variables marked with a confidential computing sensitive tag within a compiled microservice code; identifying unmarked variables related to the sensitive variables within the compiled microservice code; tagging the unmarked variables related to the sensitive variables with a sensitive attribute; generating debugging information entries comprising the sensitive variables and the sensitive attribute tag of the tagged unmarked variables; generating a protect flag in a debugging reply packet based on the debugging information entries; and denying data access to downstream debugger clients based on the protect flag.

Abstract: A Structured Query Language (SQL) injection detector extracts metadata of an SQL query to be submitted to an SQL database and identifies a related database schema of the SQL database. The metadata and the database schema are included in a prompt that is input to a Large Language Model (LLM), which generates an output that is responsive to the prompt. A response action is performed responsive to detecting from the output of the LLM that the SQL query is indicative of an SQL injection attack.

Abstract: An authentication system includes: a certificate authority; a central control system; a group including an unmanned vehicle that is a master vehicle and an unmanned vehicle that is a slave vehicle; a management system; and an external system. The central control system includes a first authentication information transmitting unit that transmits, to the master vehicle, first authentication information received from the certificate authority. The master vehicle includes an authentication unit that executes authentication with the slave vehicle belonging to the same group, and a second authentication information transmitting unit that transmits second authentication information including a first token with an expiration date and the first authentication information to the authenticated slave vehicle.

Abstract: Systems and methods for real-time monitoring, adjustment, and safeguarding of generative artificial intelligence (“AI”) output. The systems and methods may include a security risk assessment algorithm rules engine (“rules engine”). The rules engine may include logic-based, language-encoded, rules for weighting queries involving security risks and for flagging security risks comprising queries and outputs (“rules”). The systems and methods may include an internal compliance database. The internal compliance database may include flagged queries, flagged outputs, and the rules. The systems and methods may include an adaptive feedback loop mechanism. The systems and methods may include a generative, pre-trained, transformer (“GPT”) processor. The GPT processor may receive a plurality of queries from a plurality of users. The GPT processor may forward the plurality of queries to the rules engine for evaluation.