3results about How to "Reduce the recognition rate" patented technology

The invention relates to a multiband infrared adversarial sample generation method and device, equipment and a medium. The method comprises the following steps: constructing a three-dimensional model based on target real data, rendering to-be-optimized confrontation textures to the surface of the model by adopting a neural rendering technology, generating a confrontation texture three-dimensional model, processing the confrontation texture three-dimensional model by a differentiable neural renderer to obtain a two-dimensional rendered graph, and converting the two-dimensional rendered graph into grey-scale maps corresponding to short-wave, medium-wave and long-wave infrared rays. A mask is generated through semantic segmentation, a random background is superposed, an optimized sample matched with the real radiation characteristics of each wave band is generated in combination with style migration, and the target detection network feeds back iterative optimization confrontation textures and is finally arranged on the target surface to realize multi-band infrared interference detection. The method can realize full-band effective interference, is strong in robustness and high in concealment, is adaptive to various detection systems, and improves the target safety protection capability.

The invention provides a robust secure transmission and identification method for anti-distillation based on multi-teacher comparison, and belongs to the technical field of radio signal automatic modulation and identification. The sending end performs key-driven disturbance filtering processing on the wireless signal to be transmitted based on the shared key, generates an encrypted signal and transmits the encrypted signal; the receiving end performs inverse disturbance reconstruction on the received encrypted signal based on the shared key to obtain a decrypted signal; constructing a multi-teacher distillation system, wherein the multi-teacher distillation system comprises a plurality of teacher models and a student model; performing combined distillation training on the student model based on the output of the teacher model and the student model and the middle layer characteristics; the combined distillation training comprises output distillation and characteristic comparison distillation; and dynamically weighting a plurality of loss items generated in the multi-teacher distillation process through an adaptive loss weight adjustment mechanism based on meta-learning to obtain a modulation identification result. The identification rate of illegal receivers is effectively reduced, and the performance of legal receiving ends under interference is improved.

The application relates to a target identification method and device in a complex electromagnetic environment, which comprises the following steps: carrying out denoising processing on a target signal to be identified by using a wavelet packet threshold value to obtain a reconstructed signal; identifying the reconstructed signal according to a frequency domain self-adaptive amplitude modulation to obtain a signal type of the target signal; obtaining a corresponding radiation source individual of the target signal by using a pre-trained support vector machine; and obtaining an identification result of the target signal according to the signal type of the target signal and the corresponding radiation source individual. Through the above technical scheme, the wavelet packet threshold value is used for denoising, the noise interference is significantly reduced under a low signal-to-noise ratio, the effective part of the target signal is improved, the reconstructed signal is identified according to the frequency domain self-adaptive amplitude modulation, so that the signal type is obtained, the calculation time can be reduced, the target signal has a high identification rate, and the pre-trained support vector machine is used for obtaining the radiation source individual, so that the identification of the corresponding radiation source individual of the target signal can be efficiently completed.