{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T19:29:49Z","timestamp":1783193389160,"version":"3.54.6"},"reference-count":58,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T00:00:00Z","timestamp":1665964800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Source-camera identification tools assist image forensics investigators to associate an image with a camera. The Photo Response Non-Uniformity (PRNU) noise pattern caused by sensor imperfections has been proven to be an effective way to identify the source camera. However, the PRNU is susceptible to camera settings, scene details, image processing operations (e.g., simple low-pass filtering or JPEG compression), and counter-forensic attacks. A forensic investigator unaware of malicious counter-forensic attacks or incidental image manipulation is at risk of being misled. The spatial synchronization requirement during the matching of two PRNUs also represents a major limitation of the PRNU. To address the PRNU\u2019s fragility issue, in recent years, deep learning-based data-driven approaches have been developed to identify source-camera models. However, the source information learned by existing deep learning models is not able to distinguish individual cameras of the same model. In light of the vulnerabilities of the PRNU fingerprint and data-driven techniques, in this paper, we bring to light the existence of a new robust data-driven device-specific fingerprint in digital images that is capable of identifying individual cameras of the same model in practical forensic scenarios. We discover that the new device fingerprint is location-independent, stochastic, and globally available, which resolves the spatial synchronization issue. Unlike the PRNU, which resides in the high-frequency band, the new device fingerprint is extracted from the low- and mid-frequency bands, which resolves the fragility issue that the PRNU is unable to contend with. Our experiments on various datasets also demonstrate that the new fingerprint is highly resilient to image manipulations such as rotation, gamma correction, and aggressive JPEG compression.<\/jats:p>","DOI":"10.3390\/s22207871","type":"journal-article","created":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T05:08:02Z","timestamp":1665983282000},"page":"7871","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Beyond PRNU: Learning Robust Device-Specific Fingerprint for Source Camera Identification"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5899-5886","authenticated-orcid":false,"family":"Manisha","sequence":"first","affiliation":[{"name":"Department of Data Science and Computer Applications, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang-Tsun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Technology, Deakin University, Geelong 3216, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xufeng","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Information Technology, Deakin University, Geelong 3216, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2458-3891","authenticated-orcid":false,"given":"Karunakar A.","family":"Kotegar","sequence":"additional","affiliation":[{"name":"Department of Data Science and Computer Applications, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,10,17]]},"reference":[{"key":"ref_1","first-page":"300983","article-title":"A survey on digital camera identification methods","volume":"34","author":"Bernacki","year":"2020","journal-title":"Forensic Sci. Int. Digit. Investig."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"11551","DOI":"10.1364\/OE.14.011551","article-title":"Automatic source camera identification using the intrinsic lens radial distortion","volume":"14","author":"Lam","year":"2006","journal-title":"Opt. Express"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1109\/TIFS.2006.890307","article-title":"Nonintrusive component forensics of visual sensors using output images","volume":"2","author":"Swaminathan","year":"2007","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bayram, S., Sencar, H., Memon, N., and Avcibas, I. (2005, January 11\u201314). Source camera identification based on CFA interpolation. Proceedings of the IEEE International Conference on Image Processing 2005, Genoa, Italy.","DOI":"10.1109\/ICIP.2005.1530330"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1109\/TIFS.2009.2033749","article-title":"Accurate detection of demosaicing regularity for digital image forensics","volume":"4","author":"Cao","year":"2009","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_6","unstructured":"Chen, C., and Stamm, M.C. (2015, January 16\u201319). Camera model identification framework using an ensemble of demosaicing features. Proceedings of the 2015 IEEE International Workshop on Information Forensics and Security (WIFS), Rome, Italy."},{"key":"ref_7","unstructured":"Deng, Z., Gijsenij, A., and Zhang, J. (2011, January 6\u201313). Source camera identification using auto-white balance approximation. Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Sorrell, M.J. (2009). Digital camera source identification through JPEG quantisation. Multimedia Forensics and Security, IGI Global.","DOI":"10.4018\/978-1-59904-869-7.ch014"},{"key":"ref_9","first-page":"300916","article-title":"Towards Open-Set Forensic Source Grouping on JPEG Header Information","volume":"32","author":"Mullan","year":"2020","journal-title":"Forensic Sci. Int. Digit. Investig."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1109\/TIFS.2006.873602","article-title":"Digital camera identification from sensor pattern noise","volume":"1","author":"Lukas","year":"2006","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_11","first-page":"170","article-title":"Large scale test of sensor fingerprint camera identification","volume":"7254","author":"Goljan","year":"2009","journal-title":"Media Forensics Secur. SPIE"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.diin.2016.10.002","article-title":"Digital camera identification using PRNU: A feature based approach","volume":"19","author":"Akshatha","year":"2016","journal-title":"Digit. Investig."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1109\/TCSVT.2011.2160750","article-title":"Color-decoupled photo response non-uniformity for digital image forensics","volume":"22","author":"Li","year":"2012","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1109\/LSP.2016.2521349","article-title":"Enhancing sensor pattern noise via filtering distortion removal","volume":"23","author":"Lin","year":"2016","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1109\/TIFS.2015.2478748","article-title":"Preprocessing reference sensor pattern noise via spectrum equalization","volume":"11","author":"Lin","year":"2015","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2197","DOI":"10.1109\/TIFS.2017.2701335","article-title":"Blind PRNU-based image clustering for source identification","volume":"12","author":"Marra","year":"2017","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Capasso, P., Cimmino, L., Abate, A.F., Bruno, A., and Cattaneo, G. (2022). A PNU-Based Methodology to Improve the Reliability of Biometric Systems. Sensors, 22.","DOI":"10.3390\/s22166074"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ferrara, P., Iuliani, M., and Piva, A. (2022). PRNU-Based Video Source Attribution: Which Frames Are You Using?. J. Imaging, 8.","DOI":"10.3390\/jimaging8030057"},{"key":"ref_19","first-page":"301171","article-title":"User profiles\u2019 image clustering for digital investigations","volume":"38","author":"Rouhi","year":"2021","journal-title":"Forensic Sci. Int. Digit. Investig."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1826","DOI":"10.1109\/TCSVT.2016.2539828","article-title":"Detection of hue modification using photo response nonuniformity","volume":"27","author":"Hou","year":"2016","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Iuliani, M., Fontani, M., Shullani, D., and Piva, A. (2019). Hybrid reference-based video source identification. Sensors, 19.","DOI":"10.3390\/s19030649"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/TCSVT.2013.2276869","article-title":"Hardware architecture for video authentication using sensor pattern noise","volume":"24","author":"Pande","year":"2013","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1109\/TIFS.2010.2046268","article-title":"Source Camera Identification Using Enhanced Sensor Pattern Noise","volume":"5","author":"Li","year":"2010","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1109\/TIFS.2020.3009583","article-title":"On addressing the impact of ISO speed upon PRNU and forgery detection","volume":"16","author":"Quan","year":"2020","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.diin.2015.01.017","article-title":"Adaptive photo-response non-uniformity noise removal against image source attribution","volume":"12","author":"Dirik","year":"2015","journal-title":"Digit. Investig."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Li, C.T., Chang, C.Y., and Li, Y. (2009, January 7\u20139). On the repudiability of device identification and image integrity verification using sensor pattern noise. Proceedings of the International Conference on Information Security and Digital Forensics, London, UK.","DOI":"10.1007\/978-3-642-11530-1_3"},{"key":"ref_27","first-page":"793","article-title":"Large-scale image clustering based on camera fingerprints","volume":"12","author":"Lin","year":"2016","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1016\/j.image.2014.07.003","article-title":"Blind image clustering based on the normalized cuts criterion for camera identification","volume":"29","author":"Amerini","year":"2014","journal-title":"Signal Process. Image Commun."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13640-017-0217-y","article-title":"A fast source-oriented image clustering method for digital forensics","volume":"2017","author":"Li","year":"2017","journal-title":"EURASIP J. Image Video Process."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1016\/j.patcog.2017.09.027","article-title":"Inference of a compact representation of sensor fingerprint for source camera identification","volume":"74","author":"Li","year":"2018","journal-title":"Pattern Recognit."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Al Shaya, O., Yang, P., Ni, R., Zhao, Y., and Piva, A. (2018). A new dataset for source identification of high dynamic range images. Sensors, 18.","DOI":"10.3390\/s18113801"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1364\/OE.22.000470","article-title":"Forensic use of photo response non-uniformity of imaging sensors and a counter method","volume":"22","author":"Dirik","year":"2014","journal-title":"Opt. Express"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2277","DOI":"10.1109\/TIFS.2014.2361200","article-title":"Analysis of seam-carving-based anonymization of images against PRNU noise pattern-based source attribution","volume":"9","author":"Dirik","year":"2014","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1109\/LSP.2016.2641006","article-title":"First steps toward camera model identification with convolutional neural networks","volume":"24","author":"Bondi","year":"2016","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Tuama, A., Comby, F., and Chaumont, M. (2016, January 4\u20137). Camera model identification with the use of deep convolutional neural networks. Proceedings of the 2016 IEEE International Workshop on Information Forensics and Security (WIFS), Abu Dhabi, United Arab Emirates.","DOI":"10.1109\/WIFS.2016.7823908"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"24973","DOI":"10.1109\/ACCESS.2018.2832066","article-title":"Robust multi-classifier for camera model identification based on convolution neural network","volume":"6","author":"Yao","year":"2018","journal-title":"IEEE Access"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.patrec.2018.01.005","article-title":"Deep learning for source camera identification on mobile devices","volume":"126","author":"Narducci","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.diin.2018.08.001","article-title":"Identification of the source camera of images based on convolutional neural network","volume":"26","author":"Huang","year":"2018","journal-title":"Digit. Investig."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/j.image.2018.08.001","article-title":"Source camera model identification based on convolutional neural networks with local binary patterns coding","volume":"68","author":"Wang","year":"2018","journal-title":"Signal Process. Image Commun."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.patrec.2021.06.019","article-title":"Identification of source social network of digital images using deep neural network","volume":"150","author":"Manisha","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1701","DOI":"10.1109\/TCSVT.2021.3068294","article-title":"Dual-Domain Generative Adversarial Network for Digital Image Operation Anti-forensics","volume":"32","author":"Xie","year":"2021","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"4174","DOI":"10.1109\/TCSVT.2020.3047084","article-title":"Adversarial Analysis for Source Camera Identification","volume":"31","author":"Wang","year":"2020","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Chen, Y., Huang, Y., and Ding, X. (2017, January 17\u201320). Camera model identification with residual neural network. Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China.","DOI":"10.1109\/ICIP.2017.8297101"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.patrec.2017.10.016","article-title":"Source camera identification based on content-adaptive fusion residual networks","volume":"119","author":"Yang","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"25878","DOI":"10.1109\/ACCESS.2019.2897360","article-title":"Camera identification based on domain knowledge-driven deep multi-task learning","volume":"7","author":"Ding","year":"2019","journal-title":"IEEE Access"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"28079","DOI":"10.1007\/s11042-020-09106-y","article-title":"Deep siamese network for limited labels classification in source camera identification","volume":"79","author":"Sameer","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1109\/LSP.2020.3008855","article-title":"CNN-based fast source device identification","volume":"27","author":"Mandelli","year":"2020","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zou, Z., Yang, Y., Law, N.F.B., and Bharath, A.A. (2021). Efficient source camera identification with diversity-enhanced patch selection and deep residual prediction. Sensors, 21.","DOI":"10.3390\/s21144701"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1109\/TIFS.2007.916285","article-title":"Determining image origin and integrity using sensor noise","volume":"3","author":"Chen","year":"2008","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 11\u201314). Identity mappings in deep residual networks. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/s13635-017-0067-2","article-title":"VISION: A video and image dataset for source identification","volume":"2017","author":"Shullani","year":"2017","journal-title":"EURASIP J. Inf. Secur."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Quan, Y., Li, C.T., Zhou, Y., and Li, L. (2020, January 6\u201310). Warwick Image Forensics Dataset for Device Fingerprinting in Multimedia Forensics. Proceedings of the 2020 IEEE International Conference on Multimedia and Expo (ICME), London, UK.","DOI":"10.1109\/ICME46284.2020.9102783"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"101046","DOI":"10.1109\/ACCESS.2019.2928356","article-title":"Daxing Smartphone Identification Dataset","volume":"7","author":"Tian","year":"2019","journal-title":"IEEE Access"},{"key":"ref_55","doi-asserted-by":"crossref","unstructured":"Bruno, A., Capasso, P., Cattaneo, G., Petrillo, U.F., and Improta, R. (2022). A novel image dataset for source camera identification and image based recognition systems. Multimed. Tools Appl., 1\u201317.","DOI":"10.1007\/s11042-022-13354-5"},{"key":"ref_56","unstructured":"Cozzolino, D., and Verdoliva, L. (2018). Noiseprint: A CNN-based camera model fingerprint. arXiv."},{"key":"ref_57","unstructured":"Zuo, Z. (2018). Camera Model Identification with Convolutional Neural Networks and Image Noise Pattern, University Library, University of Illinois."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"168309","DOI":"10.1109\/ACCESS.2020.3022837","article-title":"Provenance Inference for Instagram Photos Through Device Fingerprinting","volume":"8","author":"Quan","year":"2020","journal-title":"IEEE Access"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/20\/7871\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:55:24Z","timestamp":1760144124000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/20\/7871"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,17]]},"references-count":58,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["s22207871"],"URL":"https:\/\/doi.org\/10.3390\/s22207871","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,17]]}}}