Lightweight Video Secondary-Encryption Scheme Based on YOLOv11 and a Discrete Model of Bi-Neuron HNN

In the digital age, surveillance videos face severe security threats during transmission. Chaotic systems are often used for encrypted transmission due to their sensitivity to initial conditions and unpredictability. However, existing chaotic encryption schemes are at risk of core information leakage, lack adaptive detection of targets, and are inefficient. To address these issues, this article proposes a lightweight video secondary-encryption scheme integrating YOLOv11 and a Discrete Bi-Neuron Hopfield Neural Network (DBHNN). The YOLOv11 model is used to detect sensitive objects in the video, enabling the scheme to further protect sensitive information. The hyperchaotic sequences generated by DBHNN are used for lightweight secondary-encryption: the point-to-point confusion for target detection objects. Subsequently, enhanced alternating confusion and diffusion are applied to encrypt all frames. The proposed scheme can process batch frames and perform secondary encryption on sensitive objects to enhance security. The simulations and tests show that the proposed lightweight encryption scheme has an encryption speed that is more than 5% better than other schemes, and YOLOv11 is also superior to other models in terms of accuracy and efficiency.