Median filtering detection has recently drawn much attention in image editing and image anti-forensic techniques. Current image median filtering forensics algorithms mainly extract features manually. To deal with the challenge of detecting median filtering from small-size and compressed image blocks, by taking into account of the properties of median filtering, we propose a median filtering detection method based on convolutional neural networks (CNNs), which can automatically learn and obtain features directly from the image. To our best knowledge, this is the first work of applying CNNs in median filtering image forensics. Unlike conventional CNN models, the first layer of our CNN framework is a filter layer that accepts an image as the input and outputs its median filtering residual (MFR). Then, via alternating convolutional layers and pooling layers to learn hierarchical representations, we obtain multiple features for further classification. We test the proposed method on several experiments. The results show that the proposed method achieves significant performance improvements, especially in the cut-and-paste forgery detection.Index Terms-Convolutional neural networks, deep learning, hierarchical representations, median filtering forensics.

Background Growing evidences indicate that circular RNAs (circRNAs) play an important role in the regulation of biological behavior of tumor. We aim to explore the role of circRNA in glioma and elucidate how circRNA acts. Methods Real-time PCR was used to examine the expression of circPTN in glioma tissues and normal brain tissues (NBT). Assays of dual- luciferase reporter system, biotin label RNA pull-down and FISH were used to determine that circPTN could sponge miR-145-5p and miR-330-5p. Tumor sphere formation assay was performed to determine self- renewal of glioma stem cell (GSCs). Cell counting Kit-8 (CCK8), EdU assay and flow cytometry were used to investigate proliferation and cell cycle. Intracranial xenograft was established to determine how circPTN impacts in vivo. Tumor sphere formation assay was performed to determine self- renewal of glioma stem cell (GSCs). Results We demonstrated circPTN was significantly higher expression in glioma tissues and glioma cell lines, compared with NBT and HEB (human astrocyte). In gain- and loss-of-function experiments, circPTN significantly promoted glioma growth in vitro and in vivo. Furthermore, we performed dual-luciferase reporter assays and RNA pull-down assays to verify that circPTN acts through sponging miR-145-5p and miR-330-5p. Increasing expression of circPTN rescued the inhibition of proliferation and downregulation of SOX9/ITGA5 in glioma cells by miR-145-5p/miR-330-5p. In addition, we found that circPTN promoted self-renewal and increased the expression of stemness markers (Nestin, CD133, SOX9, and SOX2) via sponging miR-145-5p. Moreover, this regulation was disappeared when circPTN binding sites in miR-145-5p were mutated. Conclusions Our results suggest that circPTN is an oncogenic factor that acts by sponging miR-145-5p/miR-330-5p in glioma.