Amit DOEGAR, Srinidhi HIRIYANNAIAH, Siddesh Gaddadevara MATT, Srinivasa Krishnarajanagar GOPALIYENGAR, Maitreyee DUTTA

Image forgery detection based on fusion of lightweight deep learning models

Image forgery detection is one of the key challenges in various real time applications, social media and online information platforms. The conventional methods of detection based on the traces of image manipulations are limited to the scope of predefined assumptions like hand-crafted features, size and contrast. In this paper, we propose a fusion based decision approach for image forgery detection. The fusion of decision is based on the lightweight deep learning models namely SqueezeNet, MobileNetV2 and ShuffleNet. The fusion decision system is implemented in two phases. First, the pretrained weights of the lightweight deep learning models are used to evaluate the forgery of the images. Secondly, the fine-tuned weights are used to compare the results of the forgery of the images with the pre-trained models. The experimental results suggest that the fusion based decision approach achieves better accuracy as compared to the state-of-the-art approaches.

PDF

___

[1] Amerini I, Uricchio T, Ballan L, Caldelli R. Localization of JPEG double compression through multi-domain convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW); Honolulu, HI, USA; 2017. pp. 1865-1871. doi: 10.1109/CVPRW.2017.233
[2] Xiao B, Wei Y, Bi X, Li W, Ma J. Image splicing forgery detection combining coarse to refined convolutional neural network and adaptive clustering. Information Sciences 2020; 511: 172-191. doi: 10.1016/j.ins.2019.09.038
[3] Zhang Y, Goh J, Win LL, Thing VL. Image region forgery detection: a deep learning approach. SG-CRC 2016; 2016: 1-11.
[4] Goh J, Thing VL. A hybrid evolutionary algorithm for feature and ensemble selection in image tampering detection. International Journal of Electronic Security and Digital Forensics 2015; 7 (1): 76-104.
[5] Sutthiwan P, Shi YQ, Zhao H, Ng TT, Su W. Markovian rake transform for digital image tampering detection. In: Shi YQ, Emmanuel S, Kankanhalli MS, Chang S-F, Radhakrishnan R (editors). Transactions on Data Hiding and Multimedia Security VI. Lecture Notes in Computer Science, Vol. 6730. Berlin, Germany: Springer; 2011, pp. 1-17.
[6] He Z, Lu W, Sun W, Huang J. Digital image splicing detection based on Markov features in DCT and DWT domain. Pattern Recognition 2012; 45 (12): 4292-4299.
[7] Chang IC, Yu JC, Chang CC. A forgery detection algorithm for exemplar-based inpainting images using multi-region relation. Image and Vision Computing 2013; 31 (1): 57-71.
[8] Rhee KH. Median filtering detection based on variations and residuals in image forensics. Turkish Journal of Electrical Engineering & Computer Science 2017; 25 (5): 3811-3826.
[9] Lamba AK, Jindal N, Sharma S. Digital image copy-move forgery detection based on discrete fractional wavelet transform. Turkish Journal of Electrical Engineering & Computer Science 2018; 26 (3): 1261-1277.
[10] Lin Z, He J, Tang X, Tang CK. Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis. Pattern Recognition 2009; 42 (11): 2492-2501.
[11] Chen YL, Hsu CT. Detecting recompression of JPEG images via periodicity analysis of compression artifacts for tampering detection. IEEE Transactions on Information Forensics and Security 2011; 6 (2): 396-406.
[12] Bianchi T, Piva A. Image forgery localization via block-grained analysis of JPEG artifacts. IEEE Transactions on Information Forensics and Security 2012; 7 (3): 1003-1017.
[13] Zach F, Riess C, Angelopoulou E. Automated image forgery detection through classification of JPEG ghosts. In: Springer 2012 Joint DAGM (German Association for Pattern Recognition) and OAGM Symposium; Berlin, Heidelberg; 2012. pp. 185-194.
[14] Thing VL, Chen Y, Cheh C. An improved double compression detection method for JPEG image forensics. In: IEEE International Symposium on Multimedia; Irvine, CA, USA; 2012. pp. 290-297.
[15] Wang W, Dong J, Tan T. Exploring DCT coefficient quantization effects for local tampering detection. IEEE Transactions on Information Forensics and Security 2014; 9 (10): 1653-1666.
[16] Amerini I, Caldelli R, Cappellini V, Picchioni F, Piva A. Estimate of PRNU noise based on different noise models for source camera identification. International Journal of Digital Crime and Forensics 2010; 2 (2): 21-33.
[17] Popescu AC, Farid H. Exposing digital forgeries in color filter array interpolated images. IEEE Transactions on Signal Processing 2005; 53 (10): 3948-3959. doi: 10.1109/TSP.2005.855406
[18] Hadji I, Wildes RP. What do we understand about convolutional networks? arXiv 2018; preprint arXiv:1803.08834.
[19] Khan A, Sohail A, Zahoora U, Qureshi AS. A survey of the recent architectures of deep convolutional neural networks. arXiv 2019; preprint arXiv:1901.06032.
[20] Rao Y, Ni J, Zhao H. Deep learning local descriptor for image splicing detection and localization. IEEE Access 2020; 8: 25611-25625.
[21] Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W et al. Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv 2017; preprint arXiv:1704.04861.
[22] Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. Mobilenetv2: Inverted residuals and linear bottlenecks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Salt Lake City, UT, USA; 2018. pp. 4510-4520.
[23] Phan-Xuan H, Le-Tien T, Nguyen-Chinh T, Do-Tieu T, Nguyen-Van Q et al. Preserving spatial information to enhance performance of image forgery classification. In: IEEE ATC International Conference on Advanced Technologies for Communications; Hanoi, Vietnam; 2019. pp. 50-55.
[24] Zhang X, Zhou X, Lin M, Sun J. ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: IEEE 2018 Conference on Computer Vision and Pattern Recognition (CVPR); Salt Lake City, UT, USA; 2018. pp. 6848-6856.
[25] Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv 2016; preprint arXiv:1602.07360.
[26] Al-Qershi OM, Khoo BE. Evaluation of copy-move forgery detection: datasets and evaluation metrics. Multimedia Tools and Applications 2018; 77 (24):31807-31833. doi: 10.1007/s11042-018-6201-4
[27] Al-Qershi OM, Khoo BE. Passive detection of copy-move forgery in digital images: state-of-the-art. Forensic Science International 2013; 231 (1-3): 284-95. doi: 10.1016/j.forsciint.2013.05.027
[28] Hakimi F, Hariri M, GharehBaghi F. Image splicing forgery detection using local binary pattern and discrete wavelet transform. In: IEEE 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI); Tehran, Iran; 2015. pp. 1074-1077.
[29] Lee JC, Chang CP, Chen WK. Detection of copy–move image forgery using histogram of orientated gradients. Information Sciences 2015; 321: 250-262. doi: 10.1016/j.ins.2015.03.009
[30] Zhou J, Ni J, Rao Y. Block-based convolutional neural network for image forgery detection. In: Springer International Workshop on Digital Watermarking; Magdeburg, Germany; 2017. pp. 65-76.
[31] Zhang J, Zhu W, Li B, Hu W, Yang J. Image copy detection based on convolutional neural networks. In: Springer Chinese Conference on Pattern Recognition; Singapore; 2016. pp. 111-121.
[32] Chen C, McCloskey S, Yu J. Image splicing detection via camera response function analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Honolulu, HI, USA; 2017. pp. 5087-5096.
[33] Bayar B, Stamm MC. A deep learning approach to universal image manipulation detection using a new convolutional layer. In: ACM 4th ACM Workshop on Information Hiding and Multimedia Security; Vigo, Spain; 2016. pp. 5-10. doi: 10.1145/2909827.2930786
[34] Bunk J, Bappy JH, Mohammed TM, Nataraj L, Flenner A et al. Detection and localization of image forgeries using resampling features and deep learning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops; Honolulu, HI, USA; 2017. pp. 1881-1889.
[35] Kuznetsov A. Digital image forgery detection using deep learning approach. Journal of Physics: Conference Series 2019; 1368 (3): 032028. doi: 10.1088/1742-6596/1368/3/032028.
[36] Zhou P, Han X, Morariu VI, Davis LS. Learning rich features for image manipulation detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Salt Lake City, UT, USA; 2018. pp. 1053-1061.
[37] Passalis N, Tefas A. Training lightweight deep convolutional neural networks using bag-of-features pooling. IEEE Transactions on Neural Networks and Learning Systems 2018; 30 (6): 1705-1715.
[38] Alipour N, Behrad A. Semantic segmentation of JPEG blocks using a deep CNN for non-aligned JPEG forgery detection and localization. Multimedia Tools and Applications 2020; 1-17. doi: 10.1007/s11042-019-08597-8
[39] Triantafyllidou D, Nousi P, Tefas A. Lightweight two-stream convolutional face detection. In: IEEE 25th European Signal Processing Conference (EUSIPCO); Kos, Greece; 2017. pp. 1190-1194. doi: 10.23919/EUSIPCO.2017.8081396
[40] Mushtaq S, Mir AH. Forgery detection using statistical features. In: IEEE Innovative Applications of Computational Intelligence on Power, Energy and Controls with their impact on Humanity (CIPECH); Ghaziabad, India; 2014. pp. 92-97. doi: 10.1109/CIPECH.2014.7019062
[41] Amerini I, Ballan L, Caldelli R, Del Bimbo A, Serra G. A sift-based forensic method for copy–move attack detection and transformation recovery. IEEE Transactions on iInformation Forensics and Security 2011; 6 (3): 1099-1110.
[42] Kekre HB, Mishra D, Halarnkar PN, Shende P, Gupta S. Digital image forgery detection using Image hashing. In: IEEE International Conference on Advances in Technology and Engineering (ICATE); Mumbai, India; 2013. pp.1-6. doi: 10.1109/ICAdTE.2013.6524736
[43] Fridrich AJ, Soukal BD, Lukáš AJ. Detection of copy-move forgery in digital images. In: Proceedings of Digital Forensic Research Workshop; Cleveland, OH, USA; 2003.
[44] Popescu AC, Farid H. Exposing digital forgeries by detecting duplicated image regions. Computer Science Technical Report 2004; TR2004-515: 1-11.
[45] Uliyan DM, Jalab HA, Wahab A, Ainuddin W, Sadeghi S. Image region duplication forgery detection based on angular radial partitioning and Harris key-points. Symmetry 2016; 8 (7): 62. doi: 10.3390/sym8070062
[46] Vaishnavi D, Subashini TS. Application of local invariant symmetry features to detect and localize image copy move forgeries. Journal of Information Security and Applications 2019; 44: 23-31. doi: 10.1016/j.jisa.2018.11.001
[47] Abdel-Basset M, Manogaran G, Fakhry AE, El-Henawy I. 2-Levels of clustering strategy to detect and locate copy-move forgery in digital images. Multimedia Tools and Applications 2018; 79: 5419-5437. doi: 10.1007/s11042- 018-6266-0