US20220045842 - SECURE BLOCKCHAIN INTEGRATED CIRCUIT

uiux

Regular

US20220045842 - SECURE BLOCKCHAIN INTEGRATED CIRCUIT

Abstract
An integrated circuit comprising a CPU coupled to a system bus, a network interface configured to interface with an external device, and a crypto neuromorphic core coupled to the system bus. The cryptographic core comprising a processor or core, an internal bus, and a non-transitory computer-readable memory, wherein the crypto neuromorphic core is isolated from the CPU and the network interface via the system bus and the crypto neuromorphic core runs its own operating system. The crypto neuromorphic core is configured to: contain a secure core comprising a secure processor and dedicated/protected memory; store a private key in the dedicated/protected memory accessible to the secure core but not accessible to other components of the crypto neuromorphic core, the central processing unit, and the network interface; add data to a blockchain using the private key via the network interface; and read data from the blockchain via the network interface.


1644721488416.png


In some examples, the AI/neuromorphic core 314 can comprise a NPU to perform neural network algorithms, including deep neural networks (DNN), convolutional neural networks (CNN), and recurrent neural networks, for image classification, natural language processing, speech recognition, etc. The AI/neuromorphic core 314 can be pre-trained or constantly retrain itself such that the AI/neuromorphic core 314 can autonomously control the other cores in the crypto neuromorphic core 302 (e.g., send/receive data or cryptocurrency through a blockchain). The AI/neuromorphic core 314 can also be trained to perform user authentication through biometrics (e.g., face recognition, voice recognition, iris or retina scans, gait recognition, fingerprint matching). For example, the AI/neuromorphic core 314 can receive input, by a secured physical channel, from biometric sensors (e.g., through I/O interface 208 of FIG. 2) and can directly facilitate the hardware wallet when valid user identification detected. In some examples, the AI/neuromorphic core 314 can serve as the brain of an IoT device, allowing it to perform cognitive tasks with human-level accuracy at a practical throughput and within a practical power budget. The functionality of the AI/neuromorphic core 314 can be exposed to a processor of an IoT device via a secure API and secure communication channels. Through this interface, the processor can be able to efficiently implement custom data processing applications by loading pre-trained neural network models into the AI/neuromorphic core 314, injecting data into it and reading back partial or complete activation results. These networks can be stored in the IoT device's or the AI/neuromorphic core's ROM at time of manufacturing, or acquired, improved and updated later. In some example, the AI/neuromorphic core 314 can provide an additional layer of security by keeping track of ongoing patterns of transactions and authentications. It can train a network to detect any anomaly in these patterns, and if an anomaly is detected, the system can default to a secure state and inform the user of the anomaly, and in certain cases, the system can remove the private key(s) and disable cryptocurrency transactions or disable the crypto neuromorphic core 302 altogether. In some examples, the AI/neuromorphic core 314 can aid the development and deployment of DApps with integrated learning.



---

Seems like interesting technology
 
Last edited:
  • Like
  • Fire
  • Wow
Reactions: 28 users

Dang Son

Regular

US20220045842 - SECURE BLOCKCHAIN INTEGRATED CIRCUIT

Abstract
An integrated circuit comprising a CPU coupled to a system bus, a network interface configured to interface with an external device, and a crypto neuromorphic core coupled to the system bus. The cryptographic core comprising a processor or core, an internal bus, and a non-transitory computer-readable memory, wherein the crypto neuromorphic core is isolated from the CPU and the network interface via the system bus and the crypto neuromorphic core runs its own operating system. The crypto neuromorphic core is configured to: contain a secure core comprising a secure processor and dedicated/protected memory; store a private key in the dedicated/protected memory accessible to the secure core but not accessible to other components of the crypto neuromorphic core, the central processing unit, and the network interface; add data to a blockchain using the private key via the network interface; and read data from the blockchain via the network interface.


View attachment 902

In some examples, the AI/neuromorphic core 314 can comprise a NPU to perform neural network algorithms, including deep neural networks (DNN), convolutional neural networks (CNN), and recurrent neural networks, for image classification, natural language processing, speech recognition, etc. The AI/neuromorphic core 314 can be pre-trained or constantly retrain itself such that the AI/neuromorphic core 314 can autonomously control the other cores in the crypto neuromorphic core 302 (e.g., send/receive data or cryptocurrency through a blockchain). The AI/neuromorphic core 314 can also be trained to perform user authentication through biometrics (e.g., face recognition, voice recognition, iris or retina scans, gait recognition, fingerprint matching). For example, the AI/neuromorphic core 314 can receive input, by a secured physical channel, from biometric sensors (e.g., through I/O interface 208 of FIG. 2) and can directly facilitate the hardware wallet when valid user identification detected. In some examples, the AI/neuromorphic core 314 can serve as the brain of an IoT device, allowing it to perform cognitive tasks with human-level accuracy at a practical throughput and within a practical power budget. The functionality of the AI/neuromorphic core 314 can be exposed to a processor of an IoT device via a secure API and secure communication channels. Through this interface, the processor can be able to efficiently implement custom data processing applications by loading pre-trained neural network models into the AI/neuromorphic core 314, injecting data into it and reading back partial or complete activation results. These networks can be stored in the IoT device's or the AI/neuromorphic core's ROM at time of manufacturing, or acquired, improved and updated later. In some example, the AI/neuromorphic core 314 can provide an additional layer of security by keeping track of ongoing patterns of transactions and authentications. It can train a network to detect any anomaly in these patterns, and if an anomaly is detected, the system can default to a secure state and inform the user of the anomaly, and in certain cases, the system can remove the private key(s) and disable cryptocurrency transactions or disable the crypto neuromorphic core 302 altogether. In some examples, the AI/neuromorphic core 314 can aid the development and deployment of DApps with integrated learning.



---

Seems like interesting technology
 
  • Like
Reactions: 1 users

Dang Son

Regular
Could be a Customer for Akida, developing a new Industrial Standard for Crypto Security ?
 
  • Like
Reactions: 5 users

uiux

Regular

Skynet Takes on Qualcomm Engineers

The Skynet project, launched by the OpenSingularity Foundation, envisions a network of intelligent machines (as in the movie “Terminator”), utilizing blockchain, IoT, and AI to create secure trusted networks of devices that can intelligently communicate with each other autonomously and on a large scale. The organization says that this will enable billions of interconnected identifiable IoT devices to participate effortlessly in a global machine-to-machine (M2M) economy powered by self-organizing AI networks with data integrity facilitated by blockchains, which provide solutions for device identity, secure decentralized micro-payments, and trusted communication.

---



---

Fairly certain I found the organisation this patent is associated with.
 
  • Like
Reactions: 7 users
Top Bottom