321 results about "Privacy preserving" patented technology

A computer system implements a unified framework integrating an adaptive elastic funnel (AEF) with a convergent intelligence fabric (CIF) for multi-agent AI collaboration. The system provides a universal multi-modal key-value subsystem for sharing partial computations, implements hybrid placement strategies for dynamic memory management, and incorporates quantum-resistant secure enclaves. The architecture integrates hardware acceleration through GPU-FPGA hybrid caching and neuromorphic processors, applies adaptive energy and thermal management across hardware generations, and implements autonomous flash resource orchestration with multi-dimensional wear management. The system orchestrates tensor workflows using hierarchical scheduling, enables cross-agent collaboration with privacy preservation, and supports continuous learning without catastrophic forgetting. This integration delivers unprecedented computational efficiency and security in high-dimensional decision-making environments while supporting incremental adoption through modular interfaces.

Systems and methods disclosed herein perform privacy-preserving evaluations of artificial intelligence (AI) agents. A first AI agent associated with a first entity obtains a machine-readable data structure defining one or more operative boundaries for a second AI agent associated with a second entity. The system generates a unique fixed reference value representing the machine-readable data structure by applying a first transformation operation set, and transmits the unique fixed reference value to a multi-agent storage to store the value. The system receives, via the multi-agent storage, a verification artifact from the second AI agent that indicates an observed value based on internal operational data of the second AI agent corresponding to the operative boundaries. The first AI agent determines a verification status of the verification artifact by comparing the unique fixed reference value with the observed value, and autonomously generates a verification record including a representation of the verification status.

A computer implemented method for governing risk actions by an artificial intelligence (AI) browser, by classifying a proposed action by the AI browser based on a large language model (LLM) as safe or risky based on AI weights or based on policy rules; initiating a step up authentication flow for a risk action; presenting an action summary and required capabilities to the user for approval; and enforcing user configured spend or scope limits on the risk action.

A system and method for real-time team intent modeling using persistent cognitive machines with federated human profiles which processes individual team member behavioral signals through geometric intent analyzers that generate high-dimensional vector representations of individual objectives and preferences. A team intent orchestrator aggregates individual vectors into collective representations within a dynamic geometric manifold that evolves based on team coordination patterns. Federated human profiles enable privacy-preserving knowledge sharing across teams through geometric abstraction techniques that preserve coordination utility while protecting individual privacy. The system implements proactive conflict detection through trajectory analysis that identifies potential coordination issues before performance impact, and provides real-time synchronization mechanisms that maintain team coordination coherence despite individual behavioral changes. Cross-team learning capabilities enable organizational intelligence development through pattern abstraction and context-aware adaptation of successful coordination strategies. The persistent cognitive architecture maintains coordination patterns across sessions and team composition changes, enabling continuous improvement through accumulated team experience.

The embodiments disclose a cryptographically governed system for contextual memory management in artificial intelligence including a Contextual Orchestration and Scoped Memory Protocol (COSMP) and a Decentralized Memory Wallet (DMW), which enforce secure, auditable, and policy-driven access to AI memory. Traditional token-based memory tracking is replaced by memory capsules secure data units with embedded access policies and tamper-evident logs 5400 organized via a distributed ledger. Access control is managed through decentralized identifiers (DIDs) and private cryptographic keys, ensuring that all memory interactions are signed, verifiable transactions. This architecture establishes a universal trust layer for AI, enabling post-hoc compliance checks and privacy-preserving audits. Applicable across domains such as national security, healthcare, and autonomous systems, the invention enforces rigorous behavioral constraints and access governance within AI memory and decision-making processes.

Artificially intelligent systems and methods for financial coaching provide personalized, fiduciary-compliant financial guidance through advanced machine learning architectures with measurable performance criteria. The systems implement privacy-preserving processing pipelines that detect personally identifiable information using multi-layered pattern recognition including regular expressions for formatted data sequences, named entity recognition with confidence thresholds above 0.85, and contextual analysis algorithms. A multi-step artificial intelligence processing workflow includes automated language detection, emotional tone classification with confidence scoring, financial profile transformation using predefined templates, context-aware question rephrasing, and semantic similarity matching employing vector embeddings with financial domain vocabulary weighting applying multiplier values between 1.3-2.0. Specialized training methodologies expand datasets through mathematical transformation functions utilizing statistical standard deviations with incremental variations between 0.5-2.0. Mood-based escalation logic automatically transfers users to human advisors when emotional indicators exceed confidence thresholds above 0.8. The systems maintain response times below 5 seconds while providing regulatory compliance through curated content sources and predefined fiduciary instruction parameters.

Systems and methods disclosed herein perform privacy-preserving evaluations of artificial intelligence (AI) agents. The system identifies an auditing AI agent from a set of auditing AI agents for assessing target AI agent sets. The system obtains a data structure that defines operative boundaries for a target AI agent set and generates a reference value by applying a first transformation operation set on the data structure. The system transmits the reference value to a multi-agent storage and receives, via the multi-agent storage, a verification artifact from the target AI agent set that indicates an observed value generated by applying a second transformation operation set on an artifact set generated by the target AI agent set. The system determines, via the auditing AI agent, a verification status and responsive to a particular artifact failing to satisfy one or more assessment metrics, generates an action set to modify the target AI agent set.

A computer system implements a unified framework integrating an adaptive elastic funnel (AEF) with a convergent intelligence fabric (CIF) for flexible and contextualized multi-agent AI and human collaboration at scale. The system provides a universal multi-modal key-value subsystem for sharing partial computations across agents, implements a hybrid greedy / non-greedy placement strategy for dynamic memory management, orchestrates dynamic computational workflows and tensor workflows using hierarchical tensor-fragment scheduling, enables cross-agent orchestration with policy-based privacy preservation, and incorporates quantum-resistant secure memory enclaves. The architecture supports continuous learning without catastrophic forgetting, compositional reasoning across modalities, and secure task execution in distributed environments. This integration enables unprecedented computational efficiency, secure collaboration, and adaptive intelligence in high-dimensional decision-making environments while supporting incremental adoption through modular interfaces.

The invention relates to a heterogeneous computing resource capability radiation scheduling method and device. The method comprises the following steps: determining computing capabilities of a plurality of receiving nodes in a radiation center; splitting the original encryption calculation task into a plurality of privacy protection calculation task packages; determining a node matching result according to the computing capabilities of the plurality of receiving nodes and the Pareto optimal solutions of the plurality of privacy protection computing task packages; distributing the plurality of privacy protection computing task packets to corresponding receiving nodes to obtain a distribution voucher of each receiving node; performing distributed verification on the distribution voucher to obtain a distributed verification result; performing multi-modal aggregation on all the distributed verification results to obtain an encrypted calculation radiation scheduling result; the problems of data privacy leakage, low resource utilization rate and insufficient task collaboration efficiency in a traditional scheduling mechanism are solved through encryption task disassembly, dynamic node matching capability, distributed verification and multi-modal aggregation, and the method has the advantages of improving data privacy, resource utilization rate and task collaboration efficiency.

A modular system designed for privacy-preserving content recognition and supplemental content delivery across web and mobile environments. The system employs lightweight character sampling and vision-based recognition to generate unique content fingerprints without storing or replicating original data. It features a hybrid processing architecture, using local computing resources for intensive tasks while optimizing performance on resource-constrained devices. Core functionalities include multi-method content fingerprinting, real-time monitoring with adaptive sampling, and secure supplemental content association. Operating entirely on the client-side, it complies with website terms of service and privacy regulations. Advanced features include AI-driven content recognition, blockchain-based verification, and granular content targeting through resizable selection interfaces. This technology enables seamless delivery of supplemental content while preserving privacy, reducing resource usage, and ensuring scalability across browsers, mobile applications, and edge devices. It is particularly applicable in industries such as education, retail, and secure data sharing.

A computing system is disclosed for classifying rendered learning-object content and generating structured metadata representing competency and depth-of-knowledge attributes. The system detects rendered instructional content within a user interface and generates a cryptographic hash of the content, which is encrypted with session metadata to form a classification request. The request is transmitted to a remote categorization engine, where the content is processed using embedding models and inference classifiers to determine one or more competency labels, knowledge depth values, and confidence scores. The classification result is encrypted and returned to the client device for interface rendering. Classification records, including feedback interactions and associated metadata, are stored for use in model retraining.

A multi-energy network double-layer optimization method and system based on privacy-preserving blockchain technology. The method comprises: constructing a microgrid lower-layer optimization model that takes the sum of an electricity purchasing cost and a gas purchasing cost as an optimization objective; collecting information of all microgrids in a cluster, converting an optimization problem of a lower-layer autonomous optimization model, and further establishing a microgrid collaborative optimization upper-layer model; while balancing supply and demand and limiting a transformer capacity within each time period, enabling the microgrids to establish, within remaining time period, an objective function with the objective of minimizing a total cost; and integrating a distributed system manager inside a blockchain system to manage a blockchain network, and finally establishing an interconnected multi-energy microgrid double-layer optimization model based on privacy-preserving blockchain technology. The energy optimization problem is modeled into a double-layer optimization problem based on blockchain technology, so that the decision-making mechanism is simpler, the optimization performance is better, the transaction process is safer, and the transaction cost is lower.

A system and method for privacy-preserving communication validation and multi-attribute trust scoring is disclosed. The system analyzes communication metadata to determine pattern legitimacy by comparing current communication patterns against relationship fingerprints without accessing communication content. The system validates relationship context between communicating parties using interaction graph analysis and historical communication data. Cross-network intelligence correlation compares current patterns against aggregated patterns across voice, email, and messaging services, creating a self-strengthening security framework that recognizes emerging threat patterns while validating legitimate communication behaviors. The system generates comprehensive multi-attribute trust assessments comprising individual trust attribute scores including engagement rate, reliability index, channel preference, temporal pattern, and behavioral pattern, combined into overall trust levels. Trust context is displayed through a user interface presenting simplified, intuitive, and actionable information with progressive disclosure capabilities, enabling informed user decisions while preserving privacy. Communication processing actions provide users with appropriate engagement options tailored to specific trust assessment results.

Computer-implemented system for real-time validation and threat mitigation for structured health transactions, including: a client policy repository that contains client-specific validation rules, consent restrictions, and risk thresholds; a trusted policy execution enclave that only allows policies and models after remote attestation of code and configuration, and decrypts and processes protected fields exclusively within the enclave; a grammatically aware streaming validator that enforces format and semantic constraints and synthesizes an auto-repair suggestion in case of parser errors, transforming inputs into a policy-compliant form with minimal changes; a hybrid risk engine that calculates rule-based and learned risk scores and furthermore evaluates a subset of features using data protection-preserving calculations to determine risk contributions without decoding selected fields; a causal graph generator that correlates related transactions over time into an entity-resolved, time-aligned graph and identifies impossibility patterns with edge-wise responsibility values; a coordinator for federated learning who updates models from client-local aggregates under differential privacy budgets and suspends aggregation when a distribution drift above a policy threshold is detected; an audit subsystem that generates zero-knowledge evidence demonstrating that selected compliance predicates for a transaction have been met without disclosing protected health information; a risk-adaptive flow control system that directs high-risk substreams into micro-quarantine sections with enhanced testing while maintaining the basic service quality for low-risk substreams; and a register that stores a validity context mark which links each decision to the identity of the policies, models, scope of consent and runtime environment used.

A federated byte latent transformer platform utilizing homomorphically-compressed and encrypted byte-level data. The system integrates dynamic entropy-based patching into federated learning to enable efficient, robust, privacy-preserving collaborative learning across distributed nodes. Client devices convert local data into dynamically sized patches based on entropy thresholds, encrypt these patches, and send them to a central server that processes them without decryption. The system offers improved robustness to input noise, enhanced character-level understanding, and better adaptation to low-resource languages compared to token-based approaches. It enables simultaneous scaling of both patch size and model size while maintaining fixed inference budgets, allowing efficient deployment on resource-constrained devices. These innovations address critical challenges in federated learning: efficiency, robustness to data heterogeneity, and privacy preservation.

Systems and methods disclosed herein perform privacy-preserving evaluations of artificial intelligence (AI) agents. A first AI agent associated with a first entity obtains a machine-readable data structure defining one or more operative boundaries for a second AI agent associated with a second entity. The system generates a unique fixed reference value representing the machine-readable data structure by applying a first transformation operation set, and transmits the unique fixed reference value to a multi-agent storage to store the value. The system receives, via the multi-agent storage, a verification artifact from the second AI agent that indicates an observed value based on internal operational data of the second AI agent corresponding to the operative boundaries. The first AI agent determines a verification status of the verification artifact by comparing the unique fixed reference value with the observed value, and autonomously generates a verification record including a representation of the verification status.

Computer-implemented methods for a large language model privacy preservation system. Aspects include receiving prompt data from a user device. Aspects further include generating pre-processed prompt data using the prompt data from the user device. Aspects also include identifying a category for the pre-processed prompt data using topic modeling. Aspects include generating normalized prompt data using the pre-processed prompt data. Aspects further include storing the category and the normalized prompt data.

A computer-implemented method of registering a user identifier in a public key infrastructure comprising a trusted device and a server is provided. The method includes the steps: receiving the user identifier as an input to the trusted device; obtaining a hash value of the user identifier; the trusted device obtaining biometric data comprising a facial image of the user; generating a public key and a privacy preserving data structure using the biometric data, encrypting the user identifier using the public key, and storing the encrypted user identifier as metadata in the privacy preserving data structure, wherein a private key for decrypting the encrypted user identifier can be generated from the privacy preserving data structure using subsequently acquired biometric data comprising the facial image of the user; generating a device token corresponding to the trusted device and obtaining a hash value of the device token, the server storing the privacy preserving data structure uniquely indexed by the hash value of the device token while using the hash value of the user identifier as a primary key, and the trusted device storing the device token.

Systems and methods are provided that allows users to execute a secure digital action that is authenticated by their digital wallet app (or wallet) on a user device or a wallet server. An identity issuer server issues a batch of verification credentials (VCs) for an identity holder to the wallet. The wallet stores the batch of VCs, respectively binds each VC in the batch of VCs with a given passkey from a plurality of passkeys, generates selective disclosures via a content generator server, and transmits the batch of VCs, as a plurality of VC presentations, to an identity verification server. An identity verification server requests and validates the plurality of VC presentations, and, responsive to validating the plurality of VC presentations, registers the plurality of device-bound passkeys respectively bound to the batch of VCs to generate a plurality of registered passkeys. In a secure digital action, after generating the plurality of registered passkeys, the identity verification server is further configured to authenticate the identity holder using one or more of the registered passkeys.

This disclosure describes methods for distributed machine learning across edge nodes. An edge node acquires new data and checks with a federated server for an updated large language model (LLM) or small learning model (SLM). If available, it downloads the update; otherwise, it uses the existing model. The edge node then trains the LLM / SLM on its new data and sends the updated model back to the server. This enables continuous, privacy-preserving model improvement with low communication overhead. Additionally, methods are provided for sequential task execution at the edge: a smart contract provides a pointer to a covariance matrix, which is loaded into a neural network. The edge node processes sensor data to generate a task output, then repeats the process for subsequent tasks using new matrices and updated models as needed.

The present invention relates to a privacy-preserving EV charging authorization and billing system, and a method for the same. The proposed system is configured to integrate permissioned blockchain with fully homomorphic encryption. The present invention aims to eliminate plaintext exposure mitigates single point of failure, by performing all authorization and billing computations on encrypted data and recoding transactions immutably, wherein an EV user securely generates encrypted authorization and billing requests using FHE-based public keys. The charging station routes these encrypted requests to the blockchain network, which records immutable encrypted transactions and verifies them via consensus. The FHE computation layer performs secure operations on the encrypted data for authorization and billing, while smart contracts execute automated verification and billing computations, ensuring transparency and auditability.

A system, method, and apparatus for estimating life-cycle impact while preserving data privacy uses federated learning to train machine learning models across multiple local clients without exposing private data. Local clients train local models on private datasets. Privatized update data from these local models may be transmitted to a central server which aggregates this data to enhance a global model. The global model is redistributed to clients, thereby improving its accuracy through successive federated learning rounds, without accessing any raw private data. Local clients can query their local models to obtain impact scores for products or processes based on the aggregated learning. A range of privacy-preserving computation protocols limit exposure of sensitive data. This cooperative framework enables collective model refinement reflective of broad data access without compromising confidentiality. The system provides accurate impact values alongside data security assurances for clients.

Methods of enabling Artificial Intelligence (Al) models to be trained in a privacy preserving manner are disclosed. A method comprises the formation of virtual cluster per privacy level and selection of a cluster head that performs the training and coordination per privacy level. A method comprises training an Al primary model on a private user data set. The Al primary model may be used to label a public data set. A secondary model may be trained using the labeled public data set. The secondary model may be shared with a network or other UEs.

A processor may receive a request to perform an operation. The processor may generate a seed derived from data required to perform the operation. The processor may generate a perturbation based on inputting the seed into a pseudorandom number generator. The processor may generate the actual result based on performing the operation. The processor may generate a perturbed result, wherein generating the perturbed result may comprise performing a second operation based on the actual result and the perturbation. The processor may return the perturbed result in response to the request.

User-level privacy preservation is implemented within federated machine learning. An aggregation server may distribute a machine learning model to multiple users each including respective private datasets. Individual users may train the model using the local, private dataset to generate one or more parameter updates. Prior to sending the generated parameter updates to the aggregation server for incorporation into the machine learning model, a user may modify the parameter updates by applying respective noise values to individual ones of the parameter updates to ensure differential privacy for the dataset private to the user. The aggregation server may then receive the respective modified parameter updates from the multiple users and aggregate the updates into a single set of parameter updates to update the machine learning model. The federated machine learning may further include iteratively performing said sending, training, modifying, receiving, aggregating and updating steps.

A system and method are disclosed for generating a privacy-preserving data corpus for Artificial Intelligence (AI) training. The system comprises a relying partner (RP) computing environment and a trusted, independent identity provider (IdP) computing system. Upon a user authentication request, the IdP provides the RP with only a PII-free, persistent pseudonymous identifier (gUserID) for the user. Any authentication artifacts containing Personally Identifiable Information (PII), such as an OAuth token, are programmatically neutralized by the IdP. This is achieved by generating a transient public-private encryption key pair, immediately destroying the private key, and encrypting the PII-laden artifact with the remaining public key, rendering the PII therein permanently irrecoverable. This enforcement of “PII unknowability” at the RP enables the aggregation of pseudonymous user data, linked by the persistent gUserID, from multiple independent RPs into a rich, cross-organizational corpus for AI training, without ever exposing user PII to the RP.

Privacy preservation model training includes a plurality of iterative update rounds performed on a model held by a data party of a plurality of data parties participating in training to obtain model data, which includes first shared data and local data corresponding to a shared portion and a dedicated portion of the model, respectively. The iterative training adds a perturbation to the first shared data to perform privacy preservation on at least the first shared data. The first shared data is transmitted to a server, which determines, based on first shared data of the plurality of data parties, second shared data. The shared portion of the model is updated based on the second shared data returned by the server. A next iterative update round is performed based on an updated model or using the updated model as a final model.

A data processing system implements obtaining user prompts s that include instructions to an AI application to perform one or more tasks; storing the user prompts in a prompts datastore in a secure computing environment; analyzing the user prompts using an LLM operating within the secure computing environment to generate normalized prompts based on the user prompts; extracting first n-grams from the normalized prompts using differentially private n-gram extraction that preserves user-level privacy; generating masked normalized prompts by comparing the normalized prompts with the first n-grams and replacing, with a placeholder n-gram, n-grams of the normalized prompts that do not match an n-gram of the first n-grams; extracting second n-grams from the masked normalized prompts using the differentially private n-gram extraction that preserves user-level privacy; outputting the second n-grams from the secure computing environment; and storing the second n-grams in an anonymized prompts datastore outside of the secure computing environment.

This disclosure describes methods for adaptive machine learning in distributed edge computing. An edge node collects local data, selects a suitable large language model (LLM) or small learning model (SLM), trains it, and shares updates with a federated server or peer nodes. Another method matches AI functions with appropriate models, uses datasets with confidence values, and applies a Kalman Filter to assign weights and update covariance matrix confidence. In collaborative training, edge nodes store trained models with per-layer covariance values, transmit them to a control node, and update models based on aggregated inputs. Blockchain may be used for secure model storage and distribution, with smart contracts managing access and updates. These approaches support efficient, privacy-preserving learning by adapting models using statistical confidence and decentralized coordination.

A modular compliance verification and audit recording system is disclosed. The system includes a plurality of hardware modules interconnected via a system communications bus, a memory storing rule sets, access profiles, and encrypted audit records, and communication circuitry configured to interface with one or more external electronic devices through a secure network gateway. The system receives and authenticates compliance data, applies stored rule sets to determine verification results, records verified events as immutable audit entries, and enforces data-minimization and redaction policies to generate privacy-protected audit information. The processed audit information is transmitted over the secure network gateway to authorized external systems. The system provides end-to-end verification, recording, and privacy preservation of compliance-related data across distributed computing environments.