Method and system for detecting adversarial attack on ship collision prevention system

Abstract

The present invention proposes a system for detecting an adversarial attack on a ship collision prevention system, the system comprising: an adversarial attack detection unit for detecting an adversarial attack on the basis of sensing data of the ship collision prevention system; and an automatic response unit for automatically responding through automatic isolation and backup system switching when an adversarial attack is detected through the adversarial attack detection unit.

Description

Method and System for Detecting Adversarial Attacks in a Ship Collision Avoidance System

[0001] The present invention relates to a method and system for detecting hostile attacks in a ship collision avoidance system, and more specifically, to a method and system for detecting and responding to hostile attacks that may occur in a ship collision avoidance system.

[0002] Recently, the shipbuilding industry has been developing smart ships and autonomous vessels through convergence with ICT with the goals of ship advancement, autonomous navigation, and the reduction of maritime accidents; additionally, there is an increasing number of applications for image-based AI technology to detect ship risks, such as docking and undocking systems, autonomous navigation systems, and collision detection systems.

[0003] A ship collision avoidance system is a technology that collects and analyzes information about itself and surrounding vessels to predict collision risks and suggest avoidance paths. The collision avoidance system has the following characteristics.

[0004] - Collecting information on vessels around the vessel via external devices

[0005] - Collision prediction using vessel position and speed information

[0006] - Provides collision warnings

[0007] - Collision avoidance through automatic steering control

[0008] While autonomous ship operation has the effect of preventing various maritime accidents caused by human error by predicting dangerous situations in advance and supporting comprehensive situational judgment and rapid decision-making, it inherently contains instability due to the negative aspects of artificial intelligence (AI), thus requiring technologies to counter these AI negative aspects.

[0009] A related prior art is Korean published patent 10-2011-0066010 (June 16, 2011).

[0010] The objective of the present invention is to provide a method and system for detecting adversarial attacks on a ship collision avoidance system that can significantly improve the security and reliability of the ship collision avoidance system and minimize potential risks caused by cyber attacks.

[0011] A hostile attack detection system for a ship collision avoidance system according to one aspect of the present invention for achieving the above technical problem may include: a hostile attack detection unit that detects a hostile attack based on sensing data of the ship collision avoidance system; and an automatic response unit that automatically responds by automatically isolating and switching to a backup system when a hostile attack is detected through the hostile attack detection unit.

[0012] In addition, in a hostile attack detection system for a ship collision avoidance system according to one aspect of the present invention, the hostile attack detection unit may include an abnormal pattern detection unit that detects an abnormal pattern based on artificial intelligence; an integrity verification unit that verifies the integrity of sensor data of the ship collision avoidance system; and a cross-verification unit that cross-verifies multi-source information.

[0013] In addition, in the adversarial attack detection system of a ship collision avoidance system according to one aspect of the present invention, the integrity verification unit can verify integrity by using an encrypted communication channel and blockchain technology for the transmission and processing of sensor data.

[0014] In addition, in a hostile attack detection system of a ship collision avoidance system according to one aspect of the present invention, the cross-verification unit can verify the accuracy of the data by cross-verifying the sensing data of the ship collision avoidance system and information collected through an Automatic Identification System (AIS) and GPS.

[0015] In addition, in the hostile attack detection system of a ship collision avoidance system according to one aspect of the present invention, the automatic response unit can establish an autonomous response system by establishing a real-time threat assessment and dynamic response strategy for hostile attacks.

[0016] In addition, a method for detecting a hostile attack of a ship collision avoidance system according to another aspect of the present invention may include: a sensing data receiving step of receiving sensing data of the ship collision avoidance system at a sensing data receiving unit; a hostile attack detection step of detecting a hostile attack at a hostile attack detection unit based on data received through the sensing data receiving step; and an automatic response step of automatically responding at an automatic response unit through automatic isolation and backup system switching when a hostile attack is detected through the hostile attack detection step.

[0017] In addition, in a method for detecting adversarial attacks of a ship collision avoidance system according to another aspect of the present invention, the adversarial attack detection step may include an abnormal pattern detection step for detecting an artificial intelligence-based abnormal pattern; an integrity verification step for verifying the integrity of sensor data of the ship collision avoidance system; and a cross-verification step for cross-verifying multi-source information.

[0018] In addition, in a method for detecting adversarial attacks of a ship collision avoidance system according to another aspect of the present invention, the integrity verification step may verify integrity by using an encrypted communication channel and blockchain technology for the transmission and processing of sensor data.

[0019] In addition, in the method for detecting hostile attacks of a ship collision avoidance system according to another aspect of the present invention, the cross-verification step can verify the accuracy of the data by cross-verifying the sensing data of the ship collision avoidance system with information collected through an Automatic Identification System (AIS) and GPS.

[0020] In addition, in the method for detecting an adversarial attack of a ship collision avoidance system according to another aspect of the present invention, the automatic response step can establish an autonomous response system by establishing a real-time threat assessment and dynamic response strategy for the adversarial attack.

[0021] According to the present invention, the security and reliability of a ship collision avoidance system can be significantly improved, and the potential risks caused by cyber attacks can be minimized.

[0022] FIG. 1 is a diagram showing the configuration of a hostile attack detection system of a ship collision prevention system according to the present invention.

[0023] FIG. 2 is a diagram showing the configuration of a hostile attack detection unit in a hostile attack detection system of a ship collision prevention system according to the present invention.

[0024] FIG. 3 is a flowchart showing the flow of a hostile attack detection method of a ship collision avoidance system according to the present invention.

[0025] Detailed information regarding the purpose, technical configuration, and the resulting operation and effects of the present invention will be more clearly understood through the detailed description based on the drawings attached to the specification of the present invention.

[0026] The terms used in this specification are used merely to describe specific embodiments and are not intended to limit the invention. For example, terms such as "composed of" or "comprising" used in this specification should not be interpreted as necessarily including all of the various components or steps described in the invention, but should be interpreted as excluding some of the components or steps, or potentially including additional components or steps. Furthermore, singular expressions used in this specification include plural expressions unless the context clearly indicates otherwise.

[0027] The present invention will be described in detail below by explaining preferred embodiments with reference to the attached drawings. The embodiments described below are provided to enable those skilled in the art to easily understand the technical concept of the present invention, and should not be interpreted as limiting the present invention; it is obvious to those skilled in the art that the embodiments of the present invention can have various applications.

[0028] Referring to FIGS. 1 to 3, we will examine the hostile attack detection system and method of a ship collision prevention system according to the present invention.

[0029] A hostile attack detection system (100) of a ship collision prevention system according to one aspect of the present invention may include a sensing data receiving unit (110) that receives sensing data based on sensing data of a ship collision prevention system, a hostile attack detection unit (120) that detects a hostile attack, and an automatic response unit (130) that automatically responds by automatically isolating and switching to a backup system when a hostile attack is detected through the hostile attack detection unit (120).

[0030] Additionally, the hostile attack detection unit (120) may include an abnormal pattern detection unit (121) that detects an abnormal pattern based on artificial intelligence, an integrity verification unit (122) that verifies the integrity of sensor data of the ship collision prevention system, and a cross-verification unit (123) that cross-verifies multi-source information.

[0031] The abnormal pattern detection unit (121) analyzes data collected from sensors connected to the ship's collision prevention system in real time to detect patterns that deviate from the normal operating range. Through this, abnormal operation or external attack can be identified.

[0032] The integrity verification unit (122) encrypts and transmits all sensor data within the vessel and verifies whether the data has not been tampered with in transit. This prevents an attacker from tampering with sensor data and providing incorrect information to the system.

[0033] In addition, the integrity verification unit (122) ensures that all data transmission between the ship's collision prevention system and the external system is protected through an encryption algorithm, thereby preventing unauthorized access from the outside.

[0034] In addition, sensor data is recorded on a blockchain network to ensure that the data is not tampered with, thereby verifying data integrity and automatically detecting any attempts by attackers to tamper with the data.

[0035] That is, the integrity verification unit (122) can verify the integrity of the sensor data transmission and processing using an encrypted communication channel and blockchain technology.

[0036] In addition, through access control and authentication mechanisms, all users accessing the system can be authenticated via authentication and role-based access control (RBAC) mechanisms, and unauthorized access can be blocked.

[0037] The cross-verification unit (123) can mutually verify information collected from various sensors and external systems through multi-source information cross-verification, select highly reliable data, and detect incorrect information.

[0038] In other words, the accuracy of the data can be verified by cross-verifying the sensing data of the aforementioned ship collision avoidance system with information collected through the Automatic Identification System (AIS) and GPS.

[0039] In addition, the automatic response unit (130) can establish an autonomous response system by establishing a real-time threat assessment and dynamic response strategy for hostile attacks.

[0040] In addition, the automatic response unit can perform automatic isolation and backup system switching.

[0041] In other words, when a hostile attack is detected, the system can automatically isolate the device or network segment that initiated the attack and switch to a backup system to restore normal operation. This effectively minimizes the impact of the attack on the entire system.

[0042] In addition, the automatic response unit (130) can perform real-time threat assessment and establish dynamic response strategies, analyze attacks in real time, and automatically establish appropriate response strategies. For example, if there is a problem with the integrity of a specific sensor or communication channel, a method to bypass or replace it can be executed immediately.

[0043] Furthermore, by introducing an AI-based decision support system, the AI ​​can perform real-time analysis during the attack detection and response process and suggest optimal response methods. This has the effect of significantly improving the system's accuracy and response speed.

[0044] In addition, the automatic response unit (130) establishes a security information sharing system with surrounding vessels, allowing for real-time sharing of security status between vessels and the exchange of information regarding potential attacks. This enables multiple vessels to cooperate to detect and respond to threats more quickly and efficiently.

[0045] In addition, real-time security status synchronization with the central control system enables the synchronization of real-time security information between the onboard collision avoidance system and the central control system, allowing the security status of the entire system to be managed and monitored centrally.

[0046] In addition, the automatic response unit (130) integrates a global threat intelligence feed into the ship collision prevention system, so that it can receive global security threat trends in real time, and thereby the ship has the effect of being able to respond immediately based on information about the latest threats.

[0047] Additionally, a method for detecting a hostile attack in a ship collision avoidance system according to another aspect of the present invention may include: a sensing data receiving step (S110) of receiving sensing data of the ship collision avoidance system in a sensing data receiving unit; a hostile attack detection step (S120) of detecting a hostile attack in a hostile attack detection unit based on the data received through the sensing data receiving step; and an automatic response step (S130) of automatically responding in an automatic response unit through automatic isolation and backup system switching when a hostile attack is detected through the hostile attack detection step.

[0048] In addition, in a method for detecting adversarial attacks of a ship collision avoidance system according to another aspect of the present invention, the adversarial attack detection step (S120) may include an abnormal pattern detection step (S121) for detecting an abnormal pattern based on artificial intelligence; an integrity verification step (S122) for verifying the integrity of sensor data of the ship collision avoidance system; and a cross-verification step (S123) for cross-verifying multi-source information.

[0049] Additionally, the integrity verification step (S122) can verify integrity by using an encrypted communication channel and blockchain technology for the transmission and processing of sensor data.

[0050] In addition, the cross-verification step (S123) can verify the accuracy of the data by cross-verifying the sensing data of the ship collision avoidance system with the information collected through the Automatic Identification System (AIS) and GPS.

[0051] In addition, the automatic response step (S130) can establish an autonomous response system through real-time threat assessment of hostile attacks (S140) and establishment of a dynamic response strategy (S150).

[0052] Additionally, the automatic response step (S130) may further include a security status synchronization step (S160) that synchronizes real-time security information between the onboard collision prevention system and the central control system through real-time security status synchronization with the central control system, thereby enabling central management and monitoring of the security status of the entire system.

[0053] That is, in the automatic response stage (S130), a global threat intelligence feed is integrated into the ship collision prevention system to receive global security threat trends in real time, thereby enabling the ship to respond immediately based on information regarding the latest threats.

[0054] Accordingly, according to the present invention, the security and reliability of the ship collision avoidance system can be significantly improved, and the potential risk caused by cyber attacks can be minimized.

[0055] The embodiments according to the present invention described above may be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc., either individually or in combination. The program instructions recorded on the computer-readable recording medium may be those specifically designed and configured for the present invention or those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. Hardware devices may be modified into one or more software modules to perform processing according to the present invention, and vice versa.

[0056] The embodiments described above are provided to enable those skilled in the art to easily understand the technical concept of the present invention, and should not be interpreted as limiting the present invention. It is obvious to those skilled in the art that the embodiments of the present invention can be modified and varied in various ways without departing from the spirit and scope of the present invention. Accordingly, such modifications or variations should be deemed to fall within the scope of the claims of the present invention.

[0057] 100: Adversarial Attack Detection System of Ship Collision Avoidance System

[0058] 110: Sensing data receiver

[0059] 120: Hostile Attack Detection Unit

[0060] 121: Abnormal pattern detection unit

[0061] 122: Integrity Verification Department

[0062] 123: Cross-validation unit

[0063] 130: Automatic Response Unit

Claims

1. A hostile attack detection unit that detects hostile attacks based on sensing data of a ship collision avoidance system; and A hostile attack detection system of a ship collision avoidance system, comprising an automatic response unit that automatically responds through automatic isolation and backup system switching when a hostile attack is detected through the above-mentioned hostile attack detection unit.

2. In Claim 1, The above hostile attack detection unit is, An anomaly pattern detection unit that detects artificial intelligence-based abnormal patterns; An integrity verification unit that verifies the integrity of sensor data of a ship collision avoidance system; and Adversarial attack detection system of a ship collision avoidance system, comprising a cross-verification unit that cross-verifies information from multiple sources.

3. In claim 2, In the above integrity verification unit, Adversarial attack detection system for a ship collision avoidance system that verifies integrity using encrypted communication channels and blockchain technology for the transmission and processing of sensor data.

4. In Claim 2, The above cross-verification unit is, A hostile attack detection system for a ship collision avoidance system that cross-verifies the accuracy of the data by cross-verifying the sensing data of the above ship collision avoidance system with information collected through the Automatic Identification System (AIS) and GPS.

5. In Claim 1, The above automatic response unit is a hostile attack detection system of a ship collision avoidance system that establishes an autonomous response system by establishing a real-time threat assessment and dynamic response strategy for hostile attacks.

6. A sensing data receiving step in which sensing data of a ship collision avoidance system is received at a sensing data receiving unit; A hostile attack detection step for detecting a hostile attack in a hostile attack detection unit based on data received through the above-mentioned sensing data reception step; and A method for detecting hostile attacks in a ship collision avoidance system, comprising an automatic response step in which, upon detection of a hostile attack through the above-mentioned hostile attack detection step, the automatic response unit automatically responds through automatic isolation and backup system switching.

7. In Claim 6, The above hostile attack detection step is, Anomaly pattern detection step for detecting artificial intelligence-based abnormal patterns; An integrity verification step for verifying the integrity of sensor data of a ship collision avoidance system; and A method for detecting adversarial attacks in a ship collision avoidance system, comprising a cross-verification step for cross-verifying information from multiple sources.

8. In Claim 7, The above integrity verification step is, A method for detecting adversarial attacks in a ship collision avoidance system, which verifies integrity using encrypted communication channels and blockchain technology for the transmission and processing of sensor data.

9. In Claim 7, The above cross-validation step is, A method for detecting adversarial attacks in a ship collision avoidance system, which cross-verifies the accuracy of the data by cross-verifying the sensing data of the ship collision avoidance system with information collected through an Automatic Identification System (AIS) and GPS.

10. In Claim 6, The above automatic response step is a method for detecting adversarial attacks in a ship collision avoidance system, which establishes an autonomous response system through real-time threat assessment of adversarial attacks and the establishment of dynamic response strategies.

Images