Attack robot detection method and detection system in multi-robot network

Abstract

The invention discloses an attack robot detection method and detection system in a multi-robot network. The method comprises the following steps: using a plurality of labels placed on a target robot for reflecting wireless signals from an adjacent robot; the target robot firstly constructing a unique signal feature matrix for each adjacent robot based on extracted rebound wireless signals; then, effectively measuring the distance between every two characteristic matrixes; then, generating a matrix containing the similarity probability between every two adjacent robots based on the measured distance; and finally, the adjacent robots at the same position or on the same path having similar signal characteristics, and based on the signal space characteristics, judging a legal robot and a malicious attacker in the adjacent robots according to a similarity matrix so as to detect a false robot forged by a Sybil attacker in the current network. Even on a lightweight robot platform only provided with a single antenna, accurate Sybil attack detection can be achieved, the structure is simple, and practicability is high.

Description

technical field [0001] The invention belongs to the field of robot network sybil attack detection, and more specifically relates to a detection method and detection system for an attacking robot in a multi-robot network. Background technique [0002] The rapid development of wireless technology has greatly facilitated the effective collaboration among small and agile robotic teams, enabling its widespread application in many real-world tasks, including urban surveillance, performing robot formations, and search in disaster scenarios and rescue work. Although the openness of the wireless medium enables efficient and fast collaborative tasks for multi-robot groups, it also exposes multi-robot networks to the threat of malicious cyber attacks. A particularly pernicious form of attack in multi-bot networks is the Sybil attack. Specifically, the Sybil attacker easily breaks the basic trust assumption in robot collaboration by forging many false identities (e.g., ID) to gain unf...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a detection method and detection system for attacking robots in a multi-robot network, which is used to solve the problem that it is difficult to apply to existing sybil attack detection in a multi-robot network due to the need for relatively complex hardware facilities and implementation conditions. Technical issues of miniaturized robots with payload capacity and hardware resources

Images