Visible to the public Deep Learning with Feature Reuse for JPEG Image Steganalysis

TitleDeep Learning with Feature Reuse for JPEG Image Steganalysis
Publication TypeConference Paper
Year of Publication2018
AuthorsYang, J., Kang, X., Wong, E. K., Shi, Y.
Conference Name2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
Keywords32-layer convolutional neural networks, bit per nonzero AC DCT coefficient, bottleneck layers, bpnzAC, CNN model, compositionality, Computer architecture, conventional SCA-GFR method, convolution, convolutional neural nets, data compression, Deep Learning, detection error rate reduction, discrete cosine transforms, distortion, feature extraction, feature reuse, Gabor filters, Image coding, Information Reuse and Security, J-UNIWARD, JPEG compressed image, JPEG image steganalysis, JPEG steganalysis methods, learning (artificial intelligence), pubcrawl, Resiliency, shared features, steganography, Training, Transform coding, weak hidden information, XuNet method
AbstractIt is challenging to detect weak hidden information in a JPEG compressed image. In this paper, we propose a 32-layer convolutional neural networks (CNNs) with feature reuse by concatenating all features from previous layers. The proposed method can improve the flow of gradient and information, and the shared features and bottleneck layers in the proposed CNN model further reduce the number of parameters dramatically. The experimental results shown that the proposed method significantly reduce the detection error rate compared with the existing JPEG steganalysis methods, e.g. state-of-the-art XuNet method and the conventional SCA-GFR method. Compared with XuNet method and conventional method SCA-GFR in detecting J-UNIWARD at 0.1 bpnzAC (bit per non-zero AC DCT coefficient), the proposed method can reduce detection error rate by 4.33% and 6.55% respectively.
DOI10.23919/APSIPA.2018.8659589
Citation Keyyang_deep_2018