A novel copyright protection scheme for digital content is presented, which is a private watermarking scheme based on the watermark embedding in the DCT domain and watermark extraction Using independent component anal...A novel copyright protection scheme for digital content is presented, which is a private watermarking scheme based on the watermark embedding in the DCT domain and watermark extraction Using independent component analysis （ICA）. The system includes the key for watermark extraction and the host image. The algorithm splits the original image into blocks and classifies these blocks based on visual masking, that is, noise visibility function （NVF）. Watermark components with different strength are inserted into chosen direct current components of DCT coefficients according to the classifier. The watermark extraction is based on the characteristic of the statistic independence of the host image, watermark and key. Principle component analysis （PCA） whitening process and FastICA techniques are introduced to ensure a blind watermark extraction without requiring the original image. Experirnental results show the proposed technique is robust under attacks such as image filtering and adding noise, cropping and resizing. In addition, the proposed private watermarking system can be improved to the application of the DTV content protection system.展开更多
Artificial intelligence has been widely used in the financial field, such as credit risk assessment, fraud detection, and stock prediction. Training deep learning models requires a significant amount of data, but fina...Artificial intelligence has been widely used in the financial field, such as credit risk assessment, fraud detection, and stock prediction. Training deep learning models requires a significant amount of data, but financial data often contains sensitive information, some of which cannot be disclosed. Acquiring large amounts of financial data for training deep learning models is a pressing issue that needs to be addressed. This paper proposes a Noise Visibility Function-Differential Privacy Generative Adversarial Network (NVF-DPGAN) model, which generates privacy preserving data similar to the original data, and can be applied to data augmentation for deep learning. This study conducts experiments using financial data from China Stock Market & Accounting Research (CSMAR) database. It compares the generated data with real data from various perspectives, including mean, probability density distribution, and correlation. The experimental results show that the two datasets exhibit similar characteristics. A time series forecasting model is trained on the generated data and the real data separately, and their prediction results are closely aligned. NVF-DPGAN model is feasible and practical in terms of financial data enhancement and privacy protection. This method can also be generalized to other fields, such as the privacy protection of medical data.展开更多
基金This project was supported by the Digital TV Special Foundation of National Development and Reform Commission ofChina (040313) Home Coming Scholars Science Activity Foundation of Ministry of Personnel (20041231) the Graduate In-novation Foundation of Xidian University (innovaion 0509)
文摘A novel copyright protection scheme for digital content is presented, which is a private watermarking scheme based on the watermark embedding in the DCT domain and watermark extraction Using independent component analysis （ICA）. The system includes the key for watermark extraction and the host image. The algorithm splits the original image into blocks and classifies these blocks based on visual masking, that is, noise visibility function （NVF）. Watermark components with different strength are inserted into chosen direct current components of DCT coefficients according to the classifier. The watermark extraction is based on the characteristic of the statistic independence of the host image, watermark and key. Principle component analysis （PCA） whitening process and FastICA techniques are introduced to ensure a blind watermark extraction without requiring the original image. Experirnental results show the proposed technique is robust under attacks such as image filtering and adding noise, cropping and resizing. In addition, the proposed private watermarking system can be improved to the application of the DTV content protection system.
文摘Artificial intelligence has been widely used in the financial field, such as credit risk assessment, fraud detection, and stock prediction. Training deep learning models requires a significant amount of data, but financial data often contains sensitive information, some of which cannot be disclosed. Acquiring large amounts of financial data for training deep learning models is a pressing issue that needs to be addressed. This paper proposes a Noise Visibility Function-Differential Privacy Generative Adversarial Network (NVF-DPGAN) model, which generates privacy preserving data similar to the original data, and can be applied to data augmentation for deep learning. This study conducts experiments using financial data from China Stock Market & Accounting Research (CSMAR) database. It compares the generated data with real data from various perspectives, including mean, probability density distribution, and correlation. The experimental results show that the two datasets exhibit similar characteristics. A time series forecasting model is trained on the generated data and the real data separately, and their prediction results are closely aligned. NVF-DPGAN model is feasible and practical in terms of financial data enhancement and privacy protection. This method can also be generalized to other fields, such as the privacy protection of medical data.
