WiMi Hologram Cloud Inc (WIMI)

[StockpickerCAPC]

WIMI Hologram (WIMI.US) enables blockchain intrusion detection technology in CPS based on AI and DL to enhance CPS security.

Source
https://finance.sina.com.cn/tech/roll/2023-02-22/doc-imyhpvzy8553604.shtml

February 22, 2023

Cyber ??Physical Systems (CPS) are networks of information and physical elements that interact in feedback form. The early cyber-physical system (CPS) was basically a computer network transformation of the original industrial control system or other embedded systems, which was realized through Internet access. With the continuous development of Internet technology and industrial informatization, CPS continues to improve the ease of use and work efficiency of the system, and the application scale continues to expand. Ensuring that CPS is safe and controllable is also an important technical link to deal with the new round of industrial revolution. With the development of industrial systems With the continuous development of digitalization, cyber attacks against CPS are becoming more diverse and frequent, but production safety is the top priority. Ensuring the security and controllability of cyber-physical systems (CPS) has become an important technical basis for industrialization. Based on this, WIMI (NASDAQ: WIMI) enables blockchain intrusion detection technology in CPS based on artificial intelligence (AI) and deep learning (DL) to effectively enhance the security of CPS.

CPS has an integrated and integrated relationship with the Internet of Things, industrial control systems, and industrial Internet. It is a unity of computing process and physical process, and an intelligent system integrating computing, communication and control. There are a large number of node devices in the current intelligent manufacturing CPS system. These devices need to communicate with each other to complete the configuration of resources and improve the efficiency of production collaboration. CPS is also continuously upgraded and expanded in the process of industrial informatization development.

Dr. Gao Bo from the R&D Center of WIMI (NASDAQ: WIMI) pointed out that at the moment when the industry is highly informatized brought about by cyber-physical systems (CPS), its security has become a key technology that cannot be ignored. For this reason, WIMI has developed a Intrusion detection technology using blockchain in CPS environment:
- WIMI-ProBIDCPS technology.
The technology adopts artificial intelligence (AI) and deep learning (DL) to design an effective intrusion detection system (IDS) model for the CPS environment, and intrusion detection combined with blockchain technology can effectively improve the security of CPS.

WIMI-ProBIDCPS technology adopts feature selection technology based on Adaptive Harmony Search Algorithm (AHSA, Adaptive Harmony Search Algorithm) to correctly select feature subsets. For intrusion detection and classification, a neural network-based (GRNN) model is applied. Furthermore, the detection efficiency of the GRNN technique has been enhanced by using a hyperparameter optimizer-based algorithm, thereby enhancing the intrusion detection results. Furthermore, blockchain technology is applied to enhance security in the CPS environment.

Traditional machine learning (ML) techniques have been effective in identifying data patterns and detecting cyber attacks in IDS. But once the distribution of network nodes is quite large, it cannot effectively cover the huge data set, and the performance of detecting network attacks will also decrease. Combining advances in deep learning (DL) has inspired IDS mechanisms that can handle cyberattacks with huge data sets at present high levels of complexity. WIMI-ProBIDCPS designs a behavioral analysis based on trust-related IDS. Node reputation is considered by identifying the variance between two behavioral profiles.

Use each trust evaluation data provided to calculate its trust value, and then reinforce the learning incentive model. WIMI-ProBIDCPS designs opportunities for collaboration between edge devices and hosts (IoT devices) to implement IDS to minimize transmission loss and power consumption. In order to overcome the problems of low classification accuracy and long training time of the current deep neural network (DNN) system, and achieve an appropriate response to intrusion behavior. For host IDS, a combined Deep Belief Network (DBN) based on deep IDS is created. At the same time, network optimization and training are performed using the mini-batch gradient descent method.

Blockchain can protect the integrity of data storage and ensure process transparency, so it has the potential to be applied in the field of intrusion detection. WIMI-ProBIDCPS uses blockchain technology to improve security in the CPS environment. A blockchain is an immutable distributed dataset in which new timestamped transactions are grouped and appended to a chain of hashes of blocks. The basic blockchain protocol defines how many copies of blocks can be maintained and built in a distributed fashion. The main goal of this block is to hold a list of confirmed transactions using a cryptographic hash function. Hash functions are efficient due to subsequent properties. Blocks in the blockchain are connected to the initial genetic block and confirmed by a hash. Each block is linked by a per-hash relationship, which means that all blocks have a prior hash and are further hashed in the next block.

Any such modification to the hash will cause the chain to be broken, as the original hash is appended to the next block in the chain. Recalculating the original hash to restore the chain requires a lot of computing power. The lack of universal trust means that a distributed consensus mechanism is required for block verification in the blockchain network, and blockchain-based detection methods enhance security.

WIMI-ProBIDCPS developed a new optimized way to enable blockchain intrusion detection technology in CPS environment using deep learning model. The WIMI-ProBIDCPS technique contains different processes, namely preprocessing, for feature selection, and a technique based on Adaptive Harmonized Search Algorithm (AHSA) is designed. In addition, an optimization algorithm based on a neural network (GRNN) model is utilized to detect and classify intrusions. Furthermore, blockchain technology is applied to enhance security in the CPS environment. WIMI conducted extensive simulation analysis to ensure the enhanced performance of WIMI-ProBIDCPS technology in terms of multiple measures, thus enhancing the intrusion detection results.

The application of WIMI-ProBIDCPS has a wide range of industry markets and application scenarios. Cyber-physical system (CPS) is a multi-dimensional and complex solution. It combines industrial components through the Internet of Things (IoT) to build an effective CPS production environment. In addition, CPS can also be used in various application areas such as healthcare, smart transportation, and smart home. CPS includes the integration of physical and logical systems for the transfer of information between humans, analog and digital components. The CPS network includes network modules, sensors and actuators, and is applicable to the fields of automation, electric power, civil structure, medicine and development. CPS is a complex solution and an important technical link of the new round of industrial revolution, which is supported in an integrated way Network applications and external operations, network security is regarded as the primary technical issue of CPS, and the most complicated issue in CPS is intrusion hazard vulnerability. WIMI-ProBIDCPS will greatly improve the security and reliability of CPS, and at the same time provide basic technical support for the future intelligent era of Internet of Everything, so as to ensure the security of massive terminal equipment linking networks.