The invention relates to the technical field of information security, in particular to a radio frequency fingerprint extraction and identification method capable of resisting multipath interference, which comprises the following steps of: firstly, simulating and generating wireless channel multipath parameters of a scene based on the working scene of wireless equipment; aiming at a specific application scene of wireless communication equipment, different methods are selected to simulate a multipath channel, then, signals which are collected in a training stage and are slightly influenced by multipath of the wireless channel at a short distance are simulated through a generated wireless channel model to obtain signals which are simulated and received through different wireless channels, andthen, different wireless channel simulation receiving signals are used as a training set of a radio frequency fingerprint identification classifier for training the classifier, and finally, the classifier trained based on using different wireless channel simulation receiving signals in advance is used for carrying out radio frequency fingerprint classification identification on signals actually transmitted through a wireless channel, and the influence of a wireless multipath channel on the radio frequency fingerprint can be effectively resisted.