Search

Apparatus and Method for Diagnosing Vehicle Exhaust Increase Using Autoencoder

USPTO published patent application US20260097776A1 by Hyundai Motor Company for an apparatus and method of diagnosing causes of increased vehicle exhaust gas using autoencoder neural networks. The system receives input data including sensed values, calculates reconstruction errors between input and restored data from a pre-learned autoencoder, and diagnoses exhaust increase causes based on these errors. This AI-based diagnostic technology is relevant to automotive manufacturers and emission control systems.

AutoBrains Patents AI Driving Scenario Activation Method

USPTO published patent application US20260097785A1 assigned to AutoBrains Technologies Ltd, covering methods for AI model activation based on driving scenarios. The system uses vehicle sensor data to generate signatures, matches them against a dictionary of concept signatures, and activates appropriate AI models for autonomous driving decisions. The application was filed on October 8, 2024, under Application No. 18908831.

Energy Management AI Using Time Series Forecasting for Power Load Prediction

The USPTO published patent application US20260097684A1 disclosing an AI-based energy management system that creates synthetic training datasets to forecast power load using deep learning models. The system predicts energy storage device state of charge and controls charging operations based on projected load.

Vehicle Forward Blind Spot Object Detection System Using AI

The USPTO published patent application US20260097779A1 for an AI-based vehicle blind spot detection system that distinguishes between animate and inanimate objects. The system applies different closeness thresholds depending on object type and provides driver alerts when the vehicle's projected path intersects with detected objects within threshold distances. Inventor Andrew D. Johnson filed the application on October 9, 2024.

Tokenized Data Streaming for Multi-Modal AI in Vehicles

Tokenized data streaming for multi-modal AI in vehicles

Facilitating token use authentication for access tokens using stochastic images

USPTO granted patent US12598072B2 to Capital One Services, LLC on April 7, 2026, covering methods for facilitating token use authentication using stochastic images generated by machine learning models. The patent describes a system that detects authentication requests, retrieves previously displayed images, generates new images using stochastic ML models, and authenticates users based on image selection recognition. The patent contains 19 claims and was filed on November 10, 2023.

Data processing system peripheral device management using component certificates

USPTO granted Patent US12598081B2 to Dell Products L.P. covering methods for managing data processing systems using digital certificates to authenticate and control peripheral device functions. The system employs a management controller operating independently of the CPU to enable or disable peripheral functions including Reliability, Availability, and Serviceability (RAS) reporting. The patent establishes intellectual property rights for digital certificate-based device authentication in computing environments.

Network access using hardware-based security

USPTO granted patent US12598078B2 to Sophos Limited covering hardware-based security for network authentication. The patent describes endpoint devices using hardware-bound security systems to authenticate to enterprise networks, with cryptographically validated challenge-response protocols. The patent was applied for on February 15, 2023, under application number 18110051, with 20 claims granted.

Method for deriving a partial signature with partial verification

USPTO granted patent US12598076B2 to Orange for a method of deriving a partial cryptographic signature for a subset of messages. The invention generates anonymized signature elements and verification elements allowing selective message subset verification while maintaining signature integrity.

Detection and survival method against adversarial attacks on automated systems

The USPTO granted Patent US12598075B2 to Morgan State University covering methods for device authentication and intrusion detection in BACnet MS/TP building automation networks. The patent describes an extended message format using hashed device identifiers and physical unclonable functions (PUFs) to prevent adversaries from exploiting known device IDs. The invention reallocates data field bytes to create an extended header CRC field for transmitting authentication hashes.