{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T12:01:40Z","timestamp":1765627300500,"version":"3.48.0"},"reference-count":37,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Digital Threats"],"published-print":{"date-parts":[[2025,12,31]]},"abstract":"<jats:p>Source Camera Forensics (SCF) techniques play a crucial role in digital investigations, particularly for attributing the origin of incriminating content. While traditional SCF methods, such as Sensor Pattern Noise (SPN), perform well in verification tasks, they often fall short for large-scale screening scenarios. This article proposes a shift in evaluation focus, from verification-oriented metrics (e.g., False-Positive Rate), which aim to prevent false convictions, to investigation-oriented metrics (e.g., Recall), which prioritize minimizing evidence loss. To this end, we evaluate three approaches: the classic SPN method; CompaRe, an efficient SPN-based variant; and the Media Source Similarity Hash (MSSH), a non-SPN approach that leverages JPEG structural metadata. On a contemporary dataset, MSSH achieves perfect Recall (1.0), albeit with a lower Precision (0.25). In contrast, the classic SPN and the CompaRe approach reach higher Precision values (up to 0.6 and 0.7, respectively), but their Precision drops below 0.1 for Recall values exceeding 0.7, rendering them unsuitable for the given use case in which evidence preservation is critical. Additionally, MSSH offers a speedup of over 500\u00d7 compared to SPN-based methods and demonstrates its suitability for large-scale investigations.<\/jats:p>","DOI":"10.1145\/3748266","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T18:39:47Z","timestamp":1755196787000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Metrics Matter\u2014Source Camera Forensics for Large-Scale Investigations"],"prefix":"10.1145","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1605-3250","authenticated-orcid":false,"given":"Samantha","family":"Klier","sequence":"first","affiliation":[{"name":"Faculty of Computer Science, Research Institute CODE, University of the Bundeswehr Munich, Neubiberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9254-6398","authenticated-orcid":false,"given":"Harald","family":"Baier","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science, Research Institute CODE, University of the Bundeswehr Munich, Neubiberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,13]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.fsidi.2022.301390"},{"issue":"11","key":"e_1_3_2_3_2","doi-asserted-by":"crossref","first-page":"3801","DOI":"10.3390\/s18113801","article-title":"A new dataset for source identification of high dynamic range images","volume":"18","author":"Al Shaya Omar","year":"2018","unstructured":"Omar Al Shaya, Pengpeng Yang, Rongrong Ni, Yao Zhao, and Alessandro Piva. 2018. A new dataset for source identification of high dynamic range images. Sensors 18, 11 (2018), 3801.","journal-title":"Sensors"},{"key":"e_1_3_2_4_2","first-page":"2535","volume-title":"2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP \u201921)","author":"Albisani Chiara","year":"2021","unstructured":"Chiara Albisani, Massimo Iuliani, and Alessandro Piva. 2021. Checking PRNU usability on modern devices. In 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP \u201921). IEEE, 2535\u20132539."},{"key":"e_1_3_2_5_2","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1007\/978-3-030-69449-4_15","volume-title":"19th International Workshop on Digital Forensics and Watermarking (IWDW \u201920)","author":"Baracchi Daniele","year":"2021","unstructured":"Daniele Baracchi, Massimo Iuliani, Andrea G. Nencini, and Alessandro Piva. 2021. Facing image source attribution on iPhone X. In 19th International Workshop on Digital Forensics and Watermarking (IWDW \u201920). Springer, 196\u2013207."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3321991"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-12468-0"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-022-06743-3"},{"key":"e_1_3_2_9_2","unstructured":"Canon. 2023. Deep Learning Image Processing Technology. Retrieved November 30 2023 from https:\/\/global.canon\/en\/technology\/dl-iptechnology-2023.html"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1556-4029.2009.01150.x"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging7040069"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2007.916285"},{"key":"e_1_3_2_13_2","first-page":"233","volume-title":"23rd International Conference on Machine Learning","author":"Davis Jesse","year":"2006","unstructured":"Jesse Davis and Mark Goadrich. 2006. The relationship between precision-recall and ROC curves. In 23rd International Conference on Machine Learning, 233\u2013240."},{"key":"e_1_3_2_14_2","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1117\/12.417569","volume-title":"Enabling Technologies for Law Enforcement and Security","volume":"4232","author":"Geradts Zeno J.","year":"2001","unstructured":"Zeno J. Geradts, Jurrien Bijhold, Martijn Kieft, Kenji Kurosawa, Kenro Kuroki, and Naoki Saitoh. 2001. Methods for identification of images acquired with digital cameras. In Enabling Technologies for Law Enforcement and Security, Vol. 4232. SPIE, 505\u2013512."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/1774088.1774427"},{"key":"e_1_3_2_16_2","first-page":"170","volume-title":"Media Forensics and Security","volume":"7254","author":"Goljan Miroslav","year":"2009","unstructured":"Miroslav Goljan, Jessica Fridrich, and Tom\u00e1\u0161 Filler. 2009. Large scale test of sensor fingerprint camera identification. In Media Forensics and Security, Vol. 7254. SPIE, 170\u2013181."},{"key":"e_1_3_2_17_2","first-page":"75","volume-title":"Media Forensics and Security II","volume":"7541","author":"Goljan Miroslav","year":"2010","unstructured":"Miroslav Goljan, Jessica Fridrich, and Tom\u00e1\u0161 Filler. 2010. Managing a large database of camera fingerprints. In Media Forensics and Security II, Vol. 7541. SPIE, 75\u201386."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3070478"},{"key":"e_1_3_2_19_2","first-page":"1173","volume-title":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","author":"Kao Da-Yu","year":"2020","unstructured":"Da-Yu Kao, Ni-Chen Wu, and Fuching Tsai. 2020. A triage triangle strategy for law enforcement to reduce digital forensic backlogs. In 2020 22nd International Conference on Advanced Communication Technology (ICACT). IEEE, 1173\u20131179."},{"key":"e_1_3_2_20_2","article-title":"Media source similarity hashing (MSSH): A practical tool for large-scale media investigations","author":"Klier Samantha","year":"2025","unstructured":"Samantha Klier and Harald Baier. 2025. Media source similarity hashing (MSSH): A practical tool for large-scale media investigations. Forensic Science International: Digital Investigation (2025).","journal-title":"Forensic Science International: Digital Investigation"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.fsidi.2024.301858"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2006.873602"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3008855"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2701335"},{"key":"e_1_3_2_25_2","first-page":"44102","article-title":"A closer look at AUROC and AUPRC under class imbalance","volume":"37","author":"McDermott Matthew","year":"2024","unstructured":"Matthew McDermott, Haoran Zhang, Lasse Hansen, Giovanni Angelotti, and Jack Gallifant. 2024. A closer look at AUROC and AUPRC under class imbalance. In Advances in Neural Information Processing Systems, Vol. 37, 44102\u201344163.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.fsidi.2020.300916"},{"key":"e_1_3_2_27_2","unstructured":"National Center for Missing & Exploited Children. 2024. 2023 CyberTipline Reports by Electronic Service Providers (ESP). Retrieved from https:\/\/www.missingkids.org\/content\/dam\/missingkids\/pdfs\/2023-reports-by-esp.pdf"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging10020031"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.5555\/1795494"},{"key":"e_1_3_2_30_2","first-page":"1","volume-title":"6th International Conference on Information Technology","author":"Orozco A. L. Sandoval","year":"2013","unstructured":"A. L. Sandoval Orozco, D. M. Arenas Gonz\u00e1lez, J. Rosales Corripio, L. J. Garc\u0131a Villalba, and J. C. Hernandez-Castro. 2013. Techniques for source camera identification. In 6th International Conference on Information Technology, 1\u20139."},{"issue":"2","key":"e_1_3_2_31_2","first-page":"2","article-title":"Computer forensics field triage process model","volume":"1","author":"Rogers Marcus K.","year":"2006","unstructured":"Marcus K. Rogers, James Goldman, Rick Mislan, Timothy Wedge, and Steve Debrota. 2006. Computer forensics field triage process model. Journal of Digital Forensics, Security and Law 1, 2 (2006), 2.","journal-title":"Journal of Digital Forensics, Security and Law"},{"key":"e_1_3_2_32_2","first-page":"410","volume-title":"2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)","author":"Rosenberg Andrew","year":"2007","unstructured":"Andrew Rosenberg and Julia Hirschberg. 2007. V-measure: A conditional entropy-based external cluster evaluation measure. In 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), 410\u2013420."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-7621-5_5"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13635-017-0067-2"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2015.2415461"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2455417"},{"key":"e_1_3_2_37_2","first-page":"30","volume-title":"The JPEG Still Picture Compression Standard","author":"Wallace Gregory K.","year":"1991","unstructured":"Gregory K. Wallace. 1991. The JPEG Still Picture Compression Standard, Vol. 34. ACM, 30\u201344 pages."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323024"}],"container-title":["Digital Threats: Research and Practice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3748266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T11:59:09Z","timestamp":1765627149000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3748266"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,13]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12,31]]}},"alternative-id":["10.1145\/3748266"],"URL":"https:\/\/doi.org\/10.1145\/3748266","relation":{},"ISSN":["2692-1626","2576-5337"],"issn-type":[{"type":"print","value":"2692-1626"},{"type":"electronic","value":"2576-5337"}],"subject":[],"published":{"date-parts":[[2025,12,13]]},"assertion":[{"value":"2025-05-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}