Forensic driver identification considering an unknown suspect

• Autorzy: Dološ Klara , Meyer Conrad , Attenberger Andreas , Steinberger Jessica

Identyfikatory

DOI

10.34768/amcs-2021-0040

• Języki publikacji: EN

Abstrakty

EN

One major focus in forensics is the identification of individuals based on different kinds of evidence found at a crime scene and in the digital domain. Here, we assess the potential of using in-vehicle digital data to capture the natural driving behavior of individuals in order to identify them. We formulate a forensic scenario of a hit-and-run car accident with a known and an unknown suspect being the actual driver during the accident. Specific aims of this study are (i) to further develop a workflow for driver identification in digital forensics considering a scenario with an unknown suspect, and (ii) to assess the potential of one-class compared to multi-class classification for this task. The developed workflow demonstrates that in the application of machine learning in digital forensics it is important to decide on the statistical application, data mining or hypothesis testing in advance. Further, multi-class classification is superior to one-class classification in terms of statistical model quality. Using multi-class classification it is possible to contribute to the identification of the driver in the hit-and-run accident in both types of application, data mining and hypothesis testing. Model quality is in the range of already employed methods for forensic identification of individuals.

Słowa kluczowe

EN

natural driving behavior; digital biometry; OCC; CAN-BUS data

PL

zachowanie podczas jazdy; biometria cyfrowa; OCC

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2021
• Tom: Vol. 31, no. 4
• Strony: 587--599
• Opis fizyczny: Bibliogr. 50 poz., rys., tab., wykr.

Twórcy

autor

Dološ Klara

• Central Office for Information Technology in the Security Sector, Zamdorfer Str. 88, 81677 Munich, Germany

autor

Meyer Conrad

• Central Office for Information Technology in the Security Sector, Zamdorfer Str. 88, 81677 Munich, Germany

autor

Attenberger Andreas

• Central Office for Information Technology in the Security Sector, Zamdorfer Str. 88, 81677 Munich, Germany

autor

Steinberger Jessica

• Central Office for Information Technology in the Security Sector, Zamdorfer Str. 88, 81677 Munich, Germany

Bibliografia

• [1] Acien, A., Morales, A., Vera-Rodriguez, R., Fierrez, J. and Monaco, J.V. (2020). TypeNet: Scaling up keystroke biometrics, International Joint Conference on Biometrics (IJCB), Houston, USA, pp. 1–7, https://ieeexplor e.ieee.org/document/9304908/.
• [2] Antal, M. and Szabo, L.Z. (2015). An evaluation of one-class and two-class classification algorithms for keystroke dynamics authentication on mobile devices, 20th International Conference on Control Systems and Computer Science, Bucharest, Romania, pp. 343–350, http://ieeexplore.ieee.org/document/7168452/.
• [3] Benzaoui, A., Hadid, A. and Boukrouche, A. (2014). Ear biometric recognition using local texture descriptors, Journal of Electronic Imaging 23(5): 053008, DOI:10.1117/1.JEI.23.5.053008.
• [4] Bergamini, C., Oliveira, L., Koerich, A. and Sabourin, R. (2009). Combining different biometric traits with one-class classification, Signal Processing 89(11): 2117–2127.
• [5] Bernardi, M.L., Cimitile, M., Martinelli, F. and Mercaldo, F. (2018). Driver and path detection through time-series classification, Journal of Advanced Transportation (3): 1–20.
• [6] Bouchrika, I., Goffredo, M., Carter, J. and Nixon, M. (2011). On using gait in forensic biometrics, Journal of Forensic Sciences 56(4): 882–889, DOI: 10.1111/j.1556-4029.2011.01793.x.
• [7] Breiman, L. (2001). Random forests, Machine Learning 45(1): 5–32.
• [8] Carfora, M.F., Martinelli, F., Mercaldo, F., Nardone, V., Orlando, A., Santone, A. and Vaglini, G. (2019). A “pay-how-you-drive” car insurance approach through cluster analysis, Soft Computing 23(9): 2863–2875, DOI: 10.1007/s00500-018-3274-y.
• [9] Champod, C. and Tistarelli, M. (Eds) (2017). Handbook of Biometrics for Forensic Science, Springer, Cham.
• [10] Christensen, A.M., Crowder, C.M., Ousley, S.D. and Houck, M.M. (2014). Error and its meaning in forensic science, Journal of Forensic Sciences 59(1): 123–126, DOI: 10.1111/1556-4029.12275.
• [11] Dessimoz, D. and Champod, C. (2008). Linkages between Biometrics and Forensic Science, in A.K. Jain et al. (Eds), Handbook of Biometrics, Springer, New York, pp. 425–459.
• [12] D’Lima, N. and Mittal, J. (2015). Password authentication using Keystroke Biometrics, 2015 International Conference on Communication, Information & Computing Technology (ICCICT), Mumbai, India, pp. 1–6, http://ieeexplore.ieee.org/document/7045681/.
• [13] Dološ, K., Meyer, C., Attenberger, A. and Steinberger, J. (2020). Driver identification using in-vehicle digital data in the forensic context of a hit and run accident, Forensic Science International: Digital Investigation 35: 301090.
• [14] Eude, T. and Chang, C. (2018). One-class SVM for biometric authentication by keystroke dynamics for remote evaluation, Computational Intelligence 34(1): 145–160, DOI:/10.1111/coin.12122.
• [15] Faigman, D.L. (Ed.) (2002). Modern Scientific Evidence: The Law and Science of Expert Testimony, 2nd Edn, West Group, St. Paul.
• [16] Ge, Z., Iyer, A.N., Cheluvaraja, S., Sundaram, R. and Ganapathiraju, A. (2017). Neural network based speaker classification and verification systems with enhanced features, Intelligent Systems Conference (IntelliSys), London, UK, pp. 1089–1094, http://ieeexplore.ieee.org/document/8324265/.
• [17] Glymour, C., Madigan, D., Pregibon, D. and Smyth, P. (1997). Statistical themes and lessons for data mining, Data Mining and Knowledge Discovery 1(1): 11–28.
• [18] Gross, S.R., O’Brien, B., Hu, C. and Kennedy, E. H. (2014). Rate of false conviction of criminal defendants who are sentenced to death, Proceedings of the National Academy of Sciences 111(20): 7230–7235, DOI: 10.1073/pnas.1306417111.
• [19] Gupta, S., Buriro, A. and Crispo, B. (2019). DriverAuth: A risk-based multi-modal biometric-based driver authentication scheme for ride-sharing platforms, Computers & Security 83: 122–139.
• [20] Haber, L. and Haber, R.N. (2004). Error rates for human latent fingerprint examiners, in N. Ratha and R. Bolle (Eds), Automatic Fingerprint Recognition Systems, Springer, New York, pp. 339–360, DOI: 10.1007/0-387-21685-5_17.
• [21] Helm, P. and Hagendorff, T. (2021). Beyond the prediction paradigm: Challenges for machine learning in the struggle against organized crime, Law & Contemporary Problems 84(3): 1–17.
• [22] Houck, M.M. and Budowle, B. (2002). Correlation of microscopic and mitochondrial DNA hair comparisons, Journal of Forensic Sciences 47(5): 964–967.
• [23] Ikuesan, A.R. and Venter, H.S. (2017). Digital forensic readiness framework based on behavioral-biometrics for user attribution, IEEE Conference on Application, Information and Network Security (AINS), Miri, Malaysia, pp. 54–59, http://ieeexplore.ieee.org/docu ment/8270424/.
• [24] Khan, S.S. and Madden, M.G. (2010). A survey of recent trends in one class classification, in L. Coyle and J. Freyne (Eds), Artificial Intelligence and Cognitive Science, Springer, Berlin, pp. 188–197, DOI: 10.1007/978-3-642-17080-5_21.
• [25] Kloosterman, A., Sjerps, M. and Quak, A. (2014). Error rates in forensic DNA analysis: Definition, numbers, impact and communication, Forensic Science International: Genetics 12: 77–85.
• [26] Koehler, J.J. and Liu, S. (2021). Fingerprint error rate on close non-matches, Journal of Forensic Sciences 66(1): 129–134, DOI: 10.1111/1556-4029.14580.
• [27] Koenig, B.E. (1986). Spectrographic voice identification: A forensic survey, Journal of the Acoustical Society of America 79(6): 2088–2090, DOI: 10.1121/1.393170.
• [28] Kupin, A., Moeller, B., Jiang, Y., Banerjee, N.K. and Banerjee, S. (2019). Task-driven biometric authentication of users in virtual reality (VR) environments, in I. Kompatsiaris et al. (Eds), MultiMedia Modeling, Springer, Cham, pp. 55–67, DOI: 10.1007/978-3-030-05710-7_5.
• [29] Kwak, B.I., Woo, J. and Kim, H.K. (2017). Know your master: Driver profiling-based anti-theft method, arXiv 1704.05223, http://arxiv.org/abs/1704.05223.
• [30] Liaw, A. and Wiener, M. (2002). Classification and regression by randomForest, R News 2(3): 18–22.
• [31] Lieberman, J.D., Carrell, C.A., Miethe, T.D. and Krauss, D.A. (2008). Gold versus platinum: Do jurors recognize the superiority and limitations of DNA evidence compared to other types of forensic evidence?, Psychology, Public Policy, and Law 14(1): 27–62, DOI: 10.1037/1076-8971.14.1.27.
• [32] Mack, B., Roscher, R. and Waske, B. (2014). Can I trust my one-class classification?, Remote Sensing 6(9): 8779–8802.
• [33] Mack, B. and Waske, B. (2017). In-depth comparisons of MaxEnt, biased SVM and one-class SVM for one-class classification of remote sensing data, Remote Sensing Letters 8(3): 290–299, DOI: 10.1080/2150704X.2016.1265689.
• [34] Martinelli, F., Mercaldo, F., Orlando, A., Nardone, V., Santone, A. and Sangaiah, A.K. (2020). Human behavior characterization for driving style recognition in vehicle system, Computers & Electrical Engineering 83, Article 102504, DOI: 10.1016/j.compeleceng.2017.12.050.
• [35] Mashao, D.J. and Skosan, M. (2006). Combining classifier decisions for robust speaker identification, Pattern Recognition 39(1): 147–155.
• [36] Mordini, E. (2017). Ethics and policy of forensic biometrics, in M. Tistarelli and C. Champod (Eds), Handbook of Biometrics for Forensic Science, Springer, Cham, pp. 353–365, DOI: 10.1007/978-3-319-50673-9_16.
• [37] Märkel, U. and Dološ, K. (2017). Tree species site suitability as a combination of occurrence probability and growth and derivation of priority regions for climate change adaptation, Forests 8(6): 181.
• [38] Müller, C. (Ed.) (2007). Speaker Classification I: Fundamentals, Features, and Methods, Lecture Notes in Computer Science, Vol. 4343, Springer, Berlin, DOI: 10.1007/978-3-540-74200-5.
• [39] Oshiro, T.M., Perez, P.S. and Baranauskas, J.A. (2012). How many trees in a random forest?, in D. Hutchison et al. (Eds), Machine Learning and Data Mining in Pattern Recognition, Springer, Berlin, pp. 154–168, DOI: 10.1007/978-3-642-31537-4_13.
• [40] Page, M., Taylor, J. and Blenkin, M. (2011). Forensic identification science evidence since Daubert: Part II-Judicial reasoning in decisions to exclude forensic identification evidence on grounds of reliability: Identification evidence since Daubert (II), Journal of Forensic Sciences 56(4): 913–917, DOI: 10.1111/j.1556-4029.2011.01776.x.
• [41] Remeli, M., Lestyan, S., Acs, G. and Biczok, G. (2019). Automatic driver identification from in-vehicle network logs, arXiv 1911.09508, http://arxiv.org/abs/1911.09508.
• [42] Reynolds, D. (1994). Experimental evaluation of features for robust speaker identification, IEEE Transactions on Speech and Audio Processing 2(4): 639–643.
• [43] Ross, A., Banerjee, S. and Chowdhury, A. (2020). Security in smart cities: A brief review of digital forensic schemes for biometric data, Pattern Recognition Letters 138: 346–354, DOI: 10.1016/j.patrec.2020.07.009.
• [44] Saks, M.J. and Koehler, J.J. (2005). The coming paradigm shift in forensic identification science, Science 309(5736): 892–895, DOI: 10.1126/science.1111565.
• [45] Stenzel, S., Fassnacht, F.E., Mack, B. and Schmidtlein, S. (2017). Identification of high nature value grassland with remote sensing and minimal field data, Ecological Indicators 74: 28–38.
• [46] Thompson, W. (2006). Tarnish on the “gold standard”: Recent problems in forensic DNA testing, The Champion 30: 10–16.
• [47] Tirumala, S.S., Shahamiri, S.R., Garhwal, A.S. and Wang, R. (2017). Speaker identification features extraction methods: A systematic review, Expert Systems with Applications 90: 250–271.
• [48] Turunen, E. and Dološ, K. (2021). Revealing driver’s natural behavior-A GUHA data mining approach, Mathematics 9(15): 1818.
• [49] Wakita, T., Ozawa, K., Miyajima, C., Igarashi, K., Itou, K., Takeda, K. and Itakura, F. (2005). Driver identification using driving behavior signals, IEEE Conference on Intelligent Transportation Systems, Vienna, Austria, pp. 907–912, http://ieeexplore.ieee.org/document/1520171/.
• [50] White, D., Dunn, J.D., Schmid, A.C. and Kemp, R.I. (2015). Error rates in users of automatic face recognition software, PLOS ONE 10(10): e0139827, DOI: 10.1371/journal.pone.0139827.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).