Current deep image steganography methods based on image-in-image concealment face challenges in practical applications of privacy protection and secure communication due to insufficient security of stego images and distortion in recovered secret images. To address these issues， a Conditional Generative Adversarial Network and Convolutional Block Attention Module-based image-in-image steganography method （CBAM-CGAN） was proposed. Firstly， a hybrid attention module was introduced into the generator network to enable the generator’s comprehensive learning of image features from both channel and spatial dimensions， thereby enhancing the visual quality of stego images. Secondly， residual connections were employed to reduce feature loss of secret images during network learning， and through adversarial training between the extractor and the discriminator， noise-free extraction of secret images was achieved. Finally， adversarial training between the generator and the steganalyzer was implemented to improve the stego image security. Experimental results on public datasets including COCO demonstrate that compared with steganography method StegGAN， the proposed steganography method achieves the Peak Signal-to-Noise Ratio （PSNR） improvements of 4.37 dB and 4.71 dB for stego and decrypted images， respectively， along with Structure Similarity Index Measure （SSIM） enhancements of 9.16% and 6.46%， respectively. For security， the proposed method has the detection Accuracy （Acc） against steganalyzer Ye-Net decreased by 9.35 percentage points with the False Negative Rate （FNR） increased by 12.01 percentage points. It can be seen that the proposed method ensures stego image security while achieving high-quality secret image recovery.

Hand pose estimation is an important research direction in computer vision. Traditional methods are susceptible to complex background interference， while deep learning methods， despite being more robust， still face difficulties in multi-hand scenarios and fine-grained detail recognition. Therefore， a hand pose estimation method based on mask prompts and attention mechanisms， named HMCA（Hand Mask Prompts and Attention）， was proposed. Firstly， hand mask maps， generated via object detection and semantic segmentation， were used to suppress background noise and provide prior information. Secondly， a Parallel Attention Block （PAB） and a Multi-path Residual Block （MRB） were designed to extract multi-scale features， thereby enhancing complex hand pose recognition ability， reducing computational complexity， and preventing gradient vanishing. Thirdly， the hand mask maps were utilized to guide the model to focus on hand regions， thereby addressing issues such as multi-hand and occlusion. Finally， a penalty term was incorporated into the regression loss to constrain keypoint prediction and accelerate model convergence. Experimental results show that the proposed method outperforms other methods with best performance on both the Area Under the Curve （AUC） and the Mean Per Joint Position Error （MPJPE） under varying thresholds in single-hand， multi-hand， and occlusion scenarios. On the RHD （Rendered Handpose Dataset）， an AUC of 93.22% and a MPJPE of 2.15 are achieved under varying thresholds； on the CMU Panoptic dataset， an AUC of 91.38% and a mean hand keypoint error of 2.06 are reported under varying thresholds.

Aiming at the problem that the existing speaker verification systems for anti-spoofing， with convolutional model as main part， cannot capture global feature dependency well， an speaker verification system utilizing global-local feature dependency for anti-spoofing was proposed. Firstly， for the speech spoofing detection module， two filter combination ways were designed to filter the original speech， and sample augmentation was achieved by masking the frequency sub-bands. Secondly， a multi-dimensional global attention mechanism was proposed， where the global dependencies of each dimension were obtained by pooling the channel dimension， frequency dimension， and time dimension， respectively， and the global information was fused with the original features by weighting. Finally， for the speaker verification part， a Statistical Pyramid Dense Time Delay Neural Network （SPD-TDNN） was introduced to compute the standard deviation of the features and add the global information while obtaining the multi-scale time-frequency features. Experimental results show that on ASVspoof2019 dataset， the proposed speech spoofing detection system reduces the Equal Error Rate （EER） by 65.4% compared to Audio Anti-Spoofing using Integrated Spectro-Temporal graph attention network （AASIST） model， the proposed speaker verification system for anti-spoofing reduces the spoofing-aware speaker verification EER by 97.8% compared to the separate pyramid pooling speaker verification system. The above verifies that the proposed two modules achieve better classification results with the help of global feature dependency.

To deal with the problem that the process of Gas Chromatography-Mass Spectrography (GC-MS) data is complex and time consuming which delays the whole experimental progress, taking the alignment of multiple samples as an example, a parallel framework for processing GC-MS data on Sector/Sphere was proposed, and an algorithm of aligning multiple samples in parallel was implemented. First, the similarity matrix of all the samples was computed, then the sample set was divided into small sample sets according to hierarchical clustering and samples in each set were aligned respectively, finally the results of each set were merged according to the average sample of the set. The experimental results show that the error rate of the parallel alignment algorithm is 2.9% and the speedup ratio reaches 3.29 using the cluster with 4 PC, which can speed up the process at a high accuracy, and handle the problem that the processing time is too long.