Aleksandr I. Usov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Aleksandr I. Usov has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Georgii G. Omel’yAnyuk
Peoples’ Friendship University of Russia named after Patrice Lumumba; The Russian Federal Centre of Forensic Science named after Professor A.R. Shlyakhov of the Ministry of Justice of the Russian Federation; Bauman Moscow State Technical University (BMSTU); Lomonosov Moscow State University
11 shared publications - G. I. Bebeshko
Russian Federal Centre of Forensic Science, Ministry of Justice of the Russian Federation (RFCFS), Moscow, Russia
4 shared publications - S. A. Kuz’mIn
International Research and Clinical Center ‘Intermedbiophiskhim’; Research Institute of Organic Intermediates and Dyes
4 shared publications - Svetlana Arkadyevna Smirnova
Peoples’ Friendship University of Russia named after Patrice Lumumba
4 shared publications E. S. Karpukhina
The Russian Federal Centre of Forensic Science named after professor A.R. Shlyakhov of the Ministry of Justice of the Russian Federation
3 shared publicationsI. P. Lyubetskaya
Russian Federal Centre of Forensic Science, Ministry of Justice of the Russian Federation (RFCFS), Moscow, Russia
3 shared publications
Latest Publications
- 16 November 2026
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 21 (3)
Artificial Intelligence Methodology in Forensic Examination: A Thorny Path from Technology to Evidentiary Value
The article is devoted to the conditions under which results obtained using artificial intelligence (AI) systems can have evidentiary value in forensic examination. It argues that using the single term “AI” in forensic and legal practice is an analytical error, since it groups together technologies with opposite properties–from deterministic expert systems to stochastic generative models.To address the problem, the factual architecture is proposed consisting of three complementary tools: a five-layer model of the evidence life cycle (technical-analytical, expert-interpretive, procedurallegal, organizational layers, and a meta-level); a six-category taxonomy of AI technologies ordered by risk level; and eight criteria of evidence-based (determinism, explainability, validability, function, static character, data provenance, adversarial robustness, and human oversight). Drawing on two matrices –”features–technologies” and “layers–technologies” – it is demonstrated that risk is unevenly distributed and that the key vulnerability of neural-network methods lies not in their mathematical apparatus but in the version control and organizational discipline. As a relevant example, the European Network of Forensic Science Institutes (ENFSI) position is considered. The article concludes with the need to shift regulation from the names of technologies to their properties.
- 16 November 2026
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 21 (3)
Artificial Intelligence Methodology in Forensic Examination: A Thorny Path from Technology to Evidentiary Value
The article is devoted to the conditions under which results obtained using artificial intelligence (AI) systems can have evidentiary value in forensic examination. It argues that using the single term “AI” in forensic and legal practice is an analytical error, since it groups together technologies with opposite properties–from deterministic expert systems to stochastic generative models.To address the problem, the factual architecture is proposed consisting of three complementary tools: a five-layer model of the evidence life cycle (technical-analytical, expert-interpretive, procedurallegal, organizational layers, and a meta-level); a six-category taxonomy of AI technologies ordered by risk level; and eight criteria of evidence-based (determinism, explainability, validability, function, static character, data provenance, adversarial robustness, and human oversight). Drawing on two matrices –”features–technologies” and “layers–technologies” – it is demonstrated that risk is unevenly distributed and that the key vulnerability of neural-network methods lies not in their mathematical apparatus but in the version control and organizational discipline. As a relevant example, the European Network of Forensic Science Institutes (ENFSI) position is considered. The article concludes with the need to shift regulation from the names of technologies to their properties.
- Open Access
- 3 January 2026
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 20 (4) , 59-69
Modern System of Scientific and Methodological Materials on Forensic Examination in Forensic Institutions of Russian Ministry of Justice
The article considers the main problems of scientific and methodological support of forensic activities and suggests ways to solve them using the example of forensic institutions of the Ministry of Justice of Russia. It presents an overview of the definitions of scientific and methodological materials proposed by A.R. Shlyakhov. The need to develop and further improve the system of scientific and methodological materials (SMM) on forensic examination is substantiated with regard to modern conditions. The hierarchy and definitions of the SMM main types are given. It is shown that the processes of the SMM system are based on their preparation and use life cycle which represents itself the interrelated and (or) interacting types of activities, including: development (planning, coordination of scientific and methodological work (SMW), scientific guidance of SMW topics and their implementation control, SMM validation (suitability assessment) and introduction of new SMM into expert practice. Under that the SMM life cycle is five years as a rule. The need for conducting research during 2026–2027 is substantiated with the aim to develop a set of general (specific) expert methods in the following areas: criminalistic expertise, forensic engineering and technical examination; examination of materials, substances and products; socio-humanitarian examination; economic examination; biological examination. This complex will be integrated into the electronic SMM Registry which is being created to support the activities of forensic institutions of the Russian Ministry of Justice. The unified methodological platform built up for all expert specialties in the field of forensic activities will serve as a basis for bringing in progressive mechanisms for active monitoring of the scientific and methodological support level. It will also provide practical prerequisites for the artificial intelligence technologies use in forensic examination.
- 3 January 2026
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 20 (4) , 59-69
Open AccessModern System of Scientific and Methodological Materials on Forensic Examination in Forensic Institutions of Russian Ministry of Justice
The article considers the main problems of scientific and methodological support of forensic activities and suggests ways to solve them using the example of forensic institutions of the Ministry of Justice of Russia. It presents an overview of the definitions of scientific and methodological materials proposed by A.R. Shlyakhov. The need to develop and further improve the system of scientific and methodological materials (SMM) on forensic examination is substantiated with regard to modern conditions. The hierarchy and definitions of the SMM main types are given. It is shown that the processes of the SMM system are based on their preparation and use life cycle which represents itself the interrelated and (or) interacting types of activities, including: development (planning, coordination of scientific and methodological work (SMW), scientific guidance of SMW topics and their implementation control, SMM validation (suitability assessment) and introduction of new SMM into expert practice. Under that the SMM life cycle is five years as a rule. The need for conducting research during 2026–2027 is substantiated with the aim to develop a set of general (specific) expert methods in the following areas: criminalistic expertise, forensic engineering and technical examination; examination of materials, substances and products; socio-humanitarian examination; economic examination; biological examination. This complex will be integrated into the electronic SMM Registry which is being created to support the activities of forensic institutions of the Russian Ministry of Justice. The unified methodological platform built up for all expert specialties in the field of forensic activities will serve as a basis for bringing in progressive mechanisms for active monitoring of the scientific and methodological support level. It will also provide practical prerequisites for the artificial intelligence technologies use in forensic examination.
- Open Access
- 18 April 2025
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 20 (1) , 11-22
Destruction of Digital Traces when Concealing a Crime as a Challenge to Forensic Science
Detection, examination and use of digital traces of crime are important tasks of forensic science. However, the effective use of these objects is impossible in many cases due to their destruction by an offender himself or other persons. For the first time ever this article deals with a detailed scientific systematization of methods for destroying digital traces for the first time basing on domestic and foreign experience and describes a general algorithm for forensic computer-technical expert examination of the fact of destruction of digital traces of a crime as well as lost information recovery. It seems appropriate to study the patterns of criminal destruction of digital traces in close connection with provisions and results of the development of the forensic doctrine of concealment of traces of a crime by domestic scientists in the “pre-digital era”. One of the relevant tasks is also the development of domestic technical and software tools for destroyed computer information recovery.
- 18 April 2025
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 20 (1) , 11-22
Open AccessDestruction of Digital Traces when Concealing a Crime as a Challenge to Forensic Science
Detection, examination and use of digital traces of crime are important tasks of forensic science. However, the effective use of these objects is impossible in many cases due to their destruction by an offender himself or other persons. For the first time ever this article deals with a detailed scientific systematization of methods for destroying digital traces for the first time basing on domestic and foreign experience and describes a general algorithm for forensic computer-technical expert examination of the fact of destruction of digital traces of a crime as well as lost information recovery. It seems appropriate to study the patterns of criminal destruction of digital traces in close connection with provisions and results of the development of the forensic doctrine of concealment of traces of a crime by domestic scientists in the “pre-digital era”. One of the relevant tasks is also the development of domestic technical and software tools for destroyed computer information recovery.
- Open Access
- 26 October 2024
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 19 (3) , 47-57
The Role of Digital Transformation in the Development of Forensic Science
Digital transformation plays a significant role in the implementation of forensic activities due to significant current expansion of the body of evidence based on study of combined computer information received in the course of legal proceedings. The key areas of forensic activity digital transformation are considered. It is shown that the sizes of special knowledge must obligatory cover a competent understanding of modern information technologies, their functionality and development dynamics as well as their effective use feasibility in forensic activities. The combination of systematic and integrated approaches representing various aspects of expert examination makes it possible to fully implement the principles of its objectivity, comprehensiveness and completeness as key principles of forensic activities. The need in setting up and implementation of strategic projects on improving forensic activities in the context of digital transformation determines the evolvement of digital transformation doctrine of forensic science as one of the theories of forensic expertology.
- 26 October 2024
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 19 (3) , 47-57
Open AccessThe Role of Digital Transformation in the Development of Forensic Science
Digital transformation plays a significant role in the implementation of forensic activities due to significant current expansion of the body of evidence based on study of combined computer information received in the course of legal proceedings. The key areas of forensic activity digital transformation are considered. It is shown that the sizes of special knowledge must obligatory cover a competent understanding of modern information technologies, their functionality and development dynamics as well as their effective use feasibility in forensic activities. The combination of systematic and integrated approaches representing various aspects of expert examination makes it possible to fully implement the principles of its objectivity, comprehensiveness and completeness as key principles of forensic activities. The need in setting up and implementation of strategic projects on improving forensic activities in the context of digital transformation determines the evolvement of digital transformation doctrine of forensic science as one of the theories of forensic expertology.
- Open Access
- 31 July 2024
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 19 (2) , 76-87
Artificial Intelligence and ComputerForensics
. As a result of large-scale digitalization of all spheres of human activity and the rapid introduction of artificial intelligence technologies, the need has arisen for forensic support for legal proceedings in cases in which artificial intelligence has a role. The most pressing tasks solved by forensic computer expert units are the study of the facts of unlawful (mainly criminal) use of artificial intelligence, the use of artificial intelligence to create new and improve existing methods of computer forensics, forensic analysis of products using artificial intelligence technologies in order to establish compliance of the final product with the technical specifications for its creation, as well as a comprehensive forensic the analysis is carried out either within a forensic computer examination, or comprehensively, with the involvement of specialists in the field of forensic linguistics, forensic phonoscopic and other types of examinations. Identifying distortions in metadata is an illustrative example of improving forensic methods for analyzing digital images using artificial intelligence technology.
- 31 July 2024
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 19 (2) , 76-87
Open AccessArtificial Intelligence and ComputerForensics
. As a result of large-scale digitalization of all spheres of human activity and the rapid introduction of artificial intelligence technologies, the need has arisen for forensic support for legal proceedings in cases in which artificial intelligence has a role. The most pressing tasks solved by forensic computer expert units are the study of the facts of unlawful (mainly criminal) use of artificial intelligence, the use of artificial intelligence to create new and improve existing methods of computer forensics, forensic analysis of products using artificial intelligence technologies in order to establish compliance of the final product with the technical specifications for its creation, as well as a comprehensive forensic the analysis is carried out either within a forensic computer examination, or comprehensively, with the involvement of specialists in the field of forensic linguistics, forensic phonoscopic and other types of examinations. Identifying distortions in metadata is an illustrative example of improving forensic methods for analyzing digital images using artificial intelligence technology.
- 1 January 2024
- Published by Pleiades Publishing Ltd in Inorganic Materials
- Vol. 60 (1) , 93-103
Assessing the Reliability of the Forensic Technique for the Identification Study of Motor Gasoline Using Gas-Liquid Chromatography
A new approach to solving the problems of forensic examination of petroleum products, fuels, and lubricants associated with establishing whether motor gasoline belongs to a common/different identification variety is proposed. A technique for the identification of gasoline using quantitative results of chromatographic determination of controlled parameters and subsequent evaluation of the results in pairwise compared samples according to the established criteria is developed. The following parameters were selected as controlled parameters: values of research octane number (RON), concentrations of hydrocarbon groups (paraffins, isoparaffins, arenes, naphthenes, olefins) and oxygenates. Their determination was carried out using standardized methods. We used the hardware and software complex of the Chromatec-Crystal 5000 series, including the Chromatec-DHA data processing program. Estimated criteria or decision-making rules regarding the issues posed to an expert were determined to classify gasoline under one product name (generic variety), one production technology (group variety), or a common source of origin (one production batch, storage tank, etc.). The reliability of the method was assessed using a validation procedure consisting of three stages. We used a collection of AI-92 motor gasoline, selected at gas stations of four oil companies during six months of 2022 in various districts of Moscow. At the first stage, the performer analyzed 12 aliquots of each of four gasoline samples (samples that previously belonged to the common volume) at different times. It was established that the quality indicators of the proposed technique (standard deviation of the repeatability and reproducibility, expanded uncertainty, limits of the repeatability and reproducibility) for each of the determined controlled indicators did not exceed the permissible errors established by standardized methods. At the second stage of the experiment, the performer combined 12 test samples into four groups from each manufacturer (one production technology) with three samples of different production times (different batches). By comparing the discrepancies in the measured values of the same controlled indicators between pairs of samples within groups and the discrepancy in average indicators between pairs of groups, the performer establish gasolines manufactured using the same technology; gasolines produced by the same technology, but at different times (different batches); and with a probability of 95%, gasolines having a common source of origin (previously belonging to a common volume). The conclusions of the validation study matched the original data on the samples, which confirmed the correctness of the developed comparison criteria. At the third stage (blind test), the performer examined seven gasoline samples information about the composition and properties of which was not provided to him. The results of the blind test were considered satisfactory. Thus, the results of validation indicate the suitability of the methodology for solving forensic identification problems in relation to motor gasoline and the competence of the performer technique for implementation of the technique.
- 1 January 2024
- Published by Pleiades Publishing Ltd in Inorganic Materials
- Vol. 60 (1) , 93-103
Assessing the Reliability of the Forensic Technique for the Identification Study of Motor Gasoline Using Gas-Liquid Chromatography
A new approach to solving the problems of forensic examination of petroleum products, fuels, and lubricants associated with establishing whether motor gasoline belongs to a common/different identification variety is proposed. A technique for the identification of gasoline using quantitative results of chromatographic determination of controlled parameters and subsequent evaluation of the results in pairwise compared samples according to the established criteria is developed. The following parameters were selected as controlled parameters: values of research octane number (RON), concentrations of hydrocarbon groups (paraffins, isoparaffins, arenes, naphthenes, olefins) and oxygenates. Their determination was carried out using standardized methods. We used the hardware and software complex of the Chromatec-Crystal 5000 series, including the Chromatec-DHA data processing program. Estimated criteria or decision-making rules regarding the issues posed to an expert were determined to classify gasoline under one product name (generic variety), one production technology (group variety), or a common source of origin (one production batch, storage tank, etc.). The reliability of the method was assessed using a validation procedure consisting of three stages. We used a collection of AI-92 motor gasoline, selected at gas stations of four oil companies during six months of 2022 in various districts of Moscow. At the first stage, the performer analyzed 12 aliquots of each of four gasoline samples (samples that previously belonged to the common volume) at different times. It was established that the quality indicators of the proposed technique (standard deviation of the repeatability and reproducibility, expanded uncertainty, limits of the repeatability and reproducibility) for each of the determined controlled indicators did not exceed the permissible errors established by standardized methods. At the second stage of the experiment, the performer combined 12 test samples into four groups from each manufacturer (one production technology) with three samples of different production times (different batches). By comparing the discrepancies in the measured values of the same controlled indicators between pairs of samples within groups and the discrepancy in average indicators between pairs of groups, the performer establish gasolines manufactured using the same technology; gasolines produced by the same technology, but at different times (different batches); and with a probability of 95%, gasolines having a common source of origin (previously belonging to a common volume). The conclusions of the validation study matched the original data on the samples, which confirmed the correctness of the developed comparison criteria. At the third stage (blind test), the performer examined seven gasoline samples information about the composition and properties of which was not provided to him. The results of the blind test were considered satisfactory. Thus, the results of validation indicate the suitability of the methodology for solving forensic identification problems in relation to motor gasoline and the competence of the performer technique for implementation of the technique.
- 1 December 2023
- Published by Pleiades Publishing Ltd in Inorganic Materials
- Vol. 59 (14) , 1482-1487
Evaluation of the Reliability of the Qualitative Forensic Technique Microscopic Examination of Textile Fibers
Methods of qualitative analysis are widely used in various spheres of public activity, including forensic examination. Making the right decisions based on the results of qualitative analysis necessitates confirmation of the reliability (uncertainty) of the methods which can be provided by the validation procedure. However, the issues related to the validation of qualitative forensic methods are debatable in the absence general regulatory requirements for qualitative analysis methods. We consider a validation procedure of the qualitative forensic technique called microscopic examination of textile fibers, which consists in determining a complex of characteristic external features of natural and chemical textile fibers (color, color features, morphological features) using a microscope, as well as thickness and presence/absence of a matting agent for chemical fibers. These generic characteristics are used to differentiate the fibers under study in the forensic examination of fibrous materials. The reliability of the methodology and the competence of the performers were selected as validation parameters. The parameters were determined numerically by the likelihood ratio and by the values of the rate of false and true results in the total number of tests. Ten samples of natural and chemical textile fibers from the comparative collection of the Laboratory of Forensic Examination of Fibrous Materials of the RFCSE were used for validation. Three experts participating in the experiment independently identified the presence/absence of ten external signs in each of ten samples in the period of a week. Each expert tested a set of one hundred different external features, 39 of which were present in the samples and 61 were absent. When comparing the test results obtained by the expert with the corresponding regulated (known) external features, a conclusion was made about the level of true or false result for each sample. A low (1.7%) level of false results was revealed in relation to the total number of tests, and a low (2.6%) level of false results for each of the experts indicated the reliability of the technique and competence of the experts. The calculation of the likelihood ratio (LR) showed that the probability of true results in the assessment of a set of features is about 60 times (significantly more than one) higher than the probability of false results, which also indicates the reliability of the technique. The results of the validation experiment allowed us to conclude that the method is suitable for use in solving expert problems in the forensic examination of fibrous materials.
- 1 December 2023
- Published by Pleiades Publishing Ltd in Inorganic Materials
- Vol. 59 (14) , 1482-1487
Evaluation of the Reliability of the Qualitative Forensic Technique Microscopic Examination of Textile Fibers
Methods of qualitative analysis are widely used in various spheres of public activity, including forensic examination. Making the right decisions based on the results of qualitative analysis necessitates confirmation of the reliability (uncertainty) of the methods which can be provided by the validation procedure. However, the issues related to the validation of qualitative forensic methods are debatable in the absence general regulatory requirements for qualitative analysis methods. We consider a validation procedure of the qualitative forensic technique called microscopic examination of textile fibers, which consists in determining a complex of characteristic external features of natural and chemical textile fibers (color, color features, morphological features) using a microscope, as well as thickness and presence/absence of a matting agent for chemical fibers. These generic characteristics are used to differentiate the fibers under study in the forensic examination of fibrous materials. The reliability of the methodology and the competence of the performers were selected as validation parameters. The parameters were determined numerically by the likelihood ratio and by the values of the rate of false and true results in the total number of tests. Ten samples of natural and chemical textile fibers from the comparative collection of the Laboratory of Forensic Examination of Fibrous Materials of the RFCSE were used for validation. Three experts participating in the experiment independently identified the presence/absence of ten external signs in each of ten samples in the period of a week. Each expert tested a set of one hundred different external features, 39 of which were present in the samples and 61 were absent. When comparing the test results obtained by the expert with the corresponding regulated (known) external features, a conclusion was made about the level of true or false result for each sample. A low (1.7%) level of false results was revealed in relation to the total number of tests, and a low (2.6%) level of false results for each of the experts indicated the reliability of the technique and competence of the experts. The calculation of the likelihood ratio (LR) showed that the probability of true results in the assessment of a set of features is about 60 times (significantly more than one) higher than the probability of false results, which also indicates the reliability of the technique. The results of the validation experiment allowed us to conclude that the method is suitable for use in solving expert problems in the forensic examination of fibrous materials.
- Open Access
- 9 November 2023
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 18 (3) , 6-15
Forensic Ethics Examination as a New Direction of Forensic Expert Activity of the Russian Ministry of Justice
В статье рассматриваются основы применения специальных знаний в области этики при производстве судебных экспертиз информационных материалов, содержащих признаки посягательства на духовно-нравственные ценности народа Российской Федерации, нормы морали. Предлагается разработать основы судебной этиковедческой экспертизы. Обоснована целесообразность организации производства судебной этиковедческой экспертизы в судебно-экспертных учреждениях Минюста России. Определены основания ее назначения, предмет и объекты исследования, сформулированы типовые задачи, представлен примерный перечень вопросов.
- 9 November 2023
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 18 (3) , 6-15
Open AccessForensic Ethics Examination as a New Direction of Forensic Expert Activity of the Russian Ministry of Justice
В статье рассматриваются основы применения специальных знаний в области этики при производстве судебных экспертиз информационных материалов, содержащих признаки посягательства на духовно-нравственные ценности народа Российской Федерации, нормы морали. Предлагается разработать основы судебной этиковедческой экспертизы. Обоснована целесообразность организации производства судебной этиковедческой экспертизы в судебно-экспертных учреждениях Минюста России. Определены основания ее назначения, предмет и объекты исследования, сформулированы типовые задачи, представлен примерный перечень вопросов.
- Open Access
- 9 November 2023
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 18 (3) , 60-77
Artificial Intelligence in Forensic Expertology
The article reviews the issues of studying the capabilities and areas of application of artificial intelligence technologies (AI) in forensic expertology as a science of forensic examination and forensic expert activity. The authors have developed the criteria for choosing the direction for the introduction of AI in the system of forensic expertology, and specifically in its innovative section – the management system of forensic expert activity.The prospects for the development of AI technologies in forensic examination are associated with the processing of big data based on the expert situation, the reliability of the data used in AI training and further validation (assessment of suitability) of the applied training methodology, analysis of the results of AI technology. To solve organizational and legal issues of integrating AI technologies into legal proceedings and, specifically, into forensic examination, a system of standards regulating the order, algorithms and procedures for its implementation and use of is proposed. At the same time, the assessment of the suitability of the results of the use of AI in forensic examination should become an ongoing process included in the activities of each forensic expert organization. The necessary consistency of this process determines the updated paradigm of forensic examination in the conditions of functioning AI technologies in it and the cyclical nature of the entire process of their implementation and use. Process cycle is a set of sequential actions at different levels: initiation of AI technology, evaluation (suitability) of its results at the first level, adjustment and implementation of the updated version of AI technology, assessment of the next level, etc. In GOST accredited ISO/IEC 17025-2019 forensic laboratories such system activity, although not related to AI, has already been implemented, it corresponds to the PDCA cycle (P – plan, D – do, C – check study, A – act). Therefore, for such laboratories, the modification of the organization and management of the activities in the implementation of AI technologies is the most organic and acceptable. In addition, all work on AI in the field of forensic expertise should take into account the provisions of the AI Code of Ethics, which applies to relations associated with the ethical aspects of creation (design, construction, piloting) the introduction and use of AI technologies at all stages of forensic activities.
- 9 November 2023
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 18 (3) , 60-77
Open AccessArtificial Intelligence in Forensic Expertology
The article reviews the issues of studying the capabilities and areas of application of artificial intelligence technologies (AI) in forensic expertology as a science of forensic examination and forensic expert activity. The authors have developed the criteria for choosing the direction for the introduction of AI in the system of forensic expertology, and specifically in its innovative section – the management system of forensic expert activity.The prospects for the development of AI technologies in forensic examination are associated with the processing of big data based on the expert situation, the reliability of the data used in AI training and further validation (assessment of suitability) of the applied training methodology, analysis of the results of AI technology. To solve organizational and legal issues of integrating AI technologies into legal proceedings and, specifically, into forensic examination, a system of standards regulating the order, algorithms and procedures for its implementation and use of is proposed. At the same time, the assessment of the suitability of the results of the use of AI in forensic examination should become an ongoing process included in the activities of each forensic expert organization. The necessary consistency of this process determines the updated paradigm of forensic examination in the conditions of functioning AI technologies in it and the cyclical nature of the entire process of their implementation and use. Process cycle is a set of sequential actions at different levels: initiation of AI technology, evaluation (suitability) of its results at the first level, adjustment and implementation of the updated version of AI technology, assessment of the next level, etc. In GOST accredited ISO/IEC 17025-2019 forensic laboratories such system activity, although not related to AI, has already been implemented, it corresponds to the PDCA cycle (P – plan, D – do, C – check study, A – act). Therefore, for such laboratories, the modification of the organization and management of the activities in the implementation of AI technologies is the most organic and acceptable. In addition, all work on AI in the field of forensic expertise should take into account the provisions of the AI Code of Ethics, which applies to relations associated with the ethical aspects of creation (design, construction, piloting) the introduction and use of AI technologies at all stages of forensic activities.
- Open Access
- 17 May 2023
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 18 (1) , 76-96
Methodological Features of Validating Forensic Expert Techniques
The article reviews and summarizes the experience of validating forensic expert techniques in the Russian Federal Centre of Forensic Science of the Ministry of Justice of the Russian Federation. The authors point out the methodological features of practical implementation of the validation procedure. They demonstrate that the specificity, diversity, and complexity of the objects of expert study require the classification of the applied methods in terms of metrology, identification of the main validation parameters of quantitative and qualitative methods, organization of experiments, and evaluation of validation parameters using mathematical analysis methods. They also propose to divide methods into two types: forensic expert measurement methods (FMT) and forensic expert testing methods (FTT). Based on the generalization of information presented in several regulatory documents and scientific publications, the following parameters are identified for FMT: metrological characteristics or properties of the method (specificity, linearity, sensitivity, range of determined values, detection limit, quantitative determination limit) and quality indicators of the method (precision, correctness, accuracy of the analysis result, or uncertainty). When validating FTT, it is proposed to evaluate the reliability of the method and the competence of the expert.An experiment to assess validation parameters is performed using enough control samples with established characteristics of controlled indicators and with the participation of a sufficient number of experts. Requirements for control samples are provided.The authors also give examples of probabilistic evaluation of validation parameters for two qualitative testing methods: microscopic examination of textile fibers and detection of gunshot residue using scanning electron microscopy and X-ray microanalysis. The reliability of these methods is assessed by calculating the likelihood ratio, and the specificity of interpreting the results of FMT and FTT validation is noted.The decision on compliance with the requirements is made if the interval of the established extended uncertainty for the obtained result does not exceed the tolerance field. In the absence of tolerances, FMT is considered suitable for solving forensic expert tasks if the values of the extended uncertainty of the measurement results of the controlled indicator do not exceed the values established during validation. For FTT, a low probabilistic proportion of false positive and false negative results in determining the presence/absence of controlled indicators, as well as experimentally confirmed competence of the expert during validation, are indicators of the suitability of the method for its intended use
- 17 May 2023
- Published by Russian Federal Centre of Forensic Science of the Ministry of Justice (RFCFS) in Theory and Practice of Forensic Science
- Vol. 18 (1) , 76-96
Open AccessMethodological Features of Validating Forensic Expert Techniques
The article reviews and summarizes the experience of validating forensic expert techniques in the Russian Federal Centre of Forensic Science of the Ministry of Justice of the Russian Federation. The authors point out the methodological features of practical implementation of the validation procedure. They demonstrate that the specificity, diversity, and complexity of the objects of expert study require the classification of the applied methods in terms of metrology, identification of the main validation parameters of quantitative and qualitative methods, organization of experiments, and evaluation of validation parameters using mathematical analysis methods. They also propose to divide methods into two types: forensic expert measurement methods (FMT) and forensic expert testing methods (FTT). Based on the generalization of information presented in several regulatory documents and scientific publications, the following parameters are identified for FMT: metrological characteristics or properties of the method (specificity, linearity, sensitivity, range of determined values, detection limit, quantitative determination limit) and quality indicators of the method (precision, correctness, accuracy of the analysis result, or uncertainty). When validating FTT, it is proposed to evaluate the reliability of the method and the competence of the expert.An experiment to assess validation parameters is performed using enough control samples with established characteristics of controlled indicators and with the participation of a sufficient number of experts. Requirements for control samples are provided.The authors also give examples of probabilistic evaluation of validation parameters for two qualitative testing methods: microscopic examination of textile fibers and detection of gunshot residue using scanning electron microscopy and X-ray microanalysis. The reliability of these methods is assessed by calculating the likelihood ratio, and the specificity of interpreting the results of FMT and FTT validation is noted.The decision on compliance with the requirements is made if the interval of the established extended uncertainty for the obtained result does not exceed the tolerance field. In the absence of tolerances, FMT is considered suitable for solving forensic expert tasks if the values of the extended uncertainty of the measurement results of the controlled indicator do not exceed the values established during validation. For FTT, a low probabilistic proportion of false positive and false negative results in determining the presence/absence of controlled indicators, as well as experimentally confirmed competence of the expert during validation, are indicators of the suitability of the method for its intended use