Pub Date : 2012-12-01DOI: 10.1109/WIFS.2012.6412623
S. Voloshynovskiy, M. Diephuis, F. Beekhof, O. Koval, B. Keel
Nowadays, the field of physical object security based on surface microstructures lacks common and shared data for the development, testing and fair benchmarking of new identification and authentication technologies. To our knowledge, most published results are based on proprietary data that also often lacks the necessary size for statistically significant results and conclusions. Therefore, in this paper, we introduce the first publicly available documented database for the investigation of physical object authentication based on non-cloneable surface microstructure images. We have built an automatic system suitable for massive acquisition of microstructure images from flat surfaces under different light conditions and with different cameras. The samples are acquired several times, and resulting images are aligned, labelled and online available to the public for further investigation and benchmarking of new methods. In this paper, we present the statistical properties for the images originating from 5000 unique carton packages acquired 6 times each with two different cameras. Furthermore, we derive statistical authentication frameworks for the original, the random projected and binarized domains presented together with all empirical results.
{"title":"Towards reproducible results in authentication based on physical non-cloneable functions: The forensic authentication microstructure optical set (FAMOS)","authors":"S. Voloshynovskiy, M. Diephuis, F. Beekhof, O. Koval, B. Keel","doi":"10.1109/WIFS.2012.6412623","DOIUrl":"https://doi.org/10.1109/WIFS.2012.6412623","url":null,"abstract":"Nowadays, the field of physical object security based on surface microstructures lacks common and shared data for the development, testing and fair benchmarking of new identification and authentication technologies. To our knowledge, most published results are based on proprietary data that also often lacks the necessary size for statistically significant results and conclusions. Therefore, in this paper, we introduce the first publicly available documented database for the investigation of physical object authentication based on non-cloneable surface microstructure images. We have built an automatic system suitable for massive acquisition of microstructure images from flat surfaces under different light conditions and with different cameras. The samples are acquired several times, and resulting images are aligned, labelled and online available to the public for further investigation and benchmarking of new methods. In this paper, we present the statistical properties for the images originating from 5000 unique carton packages acquired 6 times each with two different cameras. Furthermore, we derive statistical authentication frameworks for the original, the random projected and binarized domains presented together with all empirical results.","PeriodicalId":396789,"journal":{"name":"2012 IEEE International Workshop on Information Forensics and Security (WIFS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124994640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/WIFS.2012.6412617
R. Merkel, J. Dittmann, C. Vielhauer
Age determination of latent fingerprints from crime scenes is an open challenge to forensic experts since several decades. In recent publications it was shown that a feature called binary pixel in combination with a contactless and non-invasive Chromatic White Light (CWL) image sensor is able to distinguish between fingerprints younger as or older than five hours with an accuracy of about 70-80%. Such approach can be seen as a very promising first step, but needs to be improved (e.g. by a fusion with additional aging features) to reach error rates that would be acceptable in legal proceedings. In the scope of this paper, two novel aging features are introduced and evaluated as opposing sub-tendencies of the classical binary pixel feature. Furthermore, Confocal Laser Scanning Microscopy (CLSM) is firstly applied to fingerprint aging evaluations. In our experiments, 200 fingerprint time series (captured every hour for 24 hours) for each the novel CLSM as well as the classical CWL device (9600 fingerprint images in total) are evaluated and compared using the classical binary pixel feature as well as both novel sub-tendency features. We show that one of such new sub-tendencies performs very well for the CLSM device (90% of curves show a strong logarithmic aging behavior), while for the CWL sensor the classical binary pixel feature performs best (87% of curves showing a strong logarithmic aging behavior). The increased performance of such new feature can be seen as very suitable for complementing the classical CWL binary pixel aging feature in a future age estimation approach.
{"title":"Novel fingerprint aging features using binary pixel sub-tendencies: A comparison of contactless CLSM and CWL sensors","authors":"R. Merkel, J. Dittmann, C. Vielhauer","doi":"10.1109/WIFS.2012.6412617","DOIUrl":"https://doi.org/10.1109/WIFS.2012.6412617","url":null,"abstract":"Age determination of latent fingerprints from crime scenes is an open challenge to forensic experts since several decades. In recent publications it was shown that a feature called binary pixel in combination with a contactless and non-invasive Chromatic White Light (CWL) image sensor is able to distinguish between fingerprints younger as or older than five hours with an accuracy of about 70-80%. Such approach can be seen as a very promising first step, but needs to be improved (e.g. by a fusion with additional aging features) to reach error rates that would be acceptable in legal proceedings. In the scope of this paper, two novel aging features are introduced and evaluated as opposing sub-tendencies of the classical binary pixel feature. Furthermore, Confocal Laser Scanning Microscopy (CLSM) is firstly applied to fingerprint aging evaluations. In our experiments, 200 fingerprint time series (captured every hour for 24 hours) for each the novel CLSM as well as the classical CWL device (9600 fingerprint images in total) are evaluated and compared using the classical binary pixel feature as well as both novel sub-tendency features. We show that one of such new sub-tendencies performs very well for the CLSM device (90% of curves show a strong logarithmic aging behavior), while for the CWL sensor the classical binary pixel feature performs best (87% of curves showing a strong logarithmic aging behavior). The increased performance of such new feature can be seen as very suitable for complementing the classical CWL binary pixel aging feature in a future age estimation approach.","PeriodicalId":396789,"journal":{"name":"2012 IEEE International Workshop on Information Forensics and Security (WIFS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125085682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/WIFS.2012.6412629
Andreas Peter, Thomas Hartmann, Sascha Müller, S. Katzenbeisser
Forensic image recognition is an important tool in many areas of law enforcement where an agency wants to prosecute possessors of illegal images. The recognition of illegal images that might have undergone human imperceptible changes (e.g., a JPEG-recompression) is commonly done by computing a perceptual image hash function of a given image and then matching this hash with perceptual hash values in a database of previously collected illegal images. To prevent privacy violation, agencies should only learn about images that have been reliably detected as illegal and nothing else. In this work, we argue that the prevalent presence of separate departments in such agencies can be used to enforce the need-to-know principle by separating duties among them. This enables us to construct the first practically efficient architecture to perform forensic image recognition in a privacy-preserving manner. By deriving unique cryptographic keys directly from the images, we can encrypt all sensitive data and ensure that only illegal images can be recovered by the law enforcement agency while all other information remains protected.
{"title":"Privacy-preserving architecture for forensic image recognition","authors":"Andreas Peter, Thomas Hartmann, Sascha Müller, S. Katzenbeisser","doi":"10.1109/WIFS.2012.6412629","DOIUrl":"https://doi.org/10.1109/WIFS.2012.6412629","url":null,"abstract":"Forensic image recognition is an important tool in many areas of law enforcement where an agency wants to prosecute possessors of illegal images. The recognition of illegal images that might have undergone human imperceptible changes (e.g., a JPEG-recompression) is commonly done by computing a perceptual image hash function of a given image and then matching this hash with perceptual hash values in a database of previously collected illegal images. To prevent privacy violation, agencies should only learn about images that have been reliably detected as illegal and nothing else. In this work, we argue that the prevalent presence of separate departments in such agencies can be used to enforce the need-to-know principle by separating duties among them. This enables us to construct the first practically efficient architecture to perform forensic image recognition in a privacy-preserving manner. By deriving unique cryptographic keys directly from the images, we can encrypt all sensitive data and ensure that only illegal images can be recovered by the law enforcement agency while all other information remains protected.","PeriodicalId":396789,"journal":{"name":"2012 IEEE International Workshop on Information Forensics and Security (WIFS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115930675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/WIFS.2012.6412638
F. Beekhof, S. Voloshynovskiy, F. Farhadzadeh
We consider the problem of content identification and authentication based on digital content fingerprinting. Contrary to existing work in which the performance of these systems under blind attacks is analysed, we investigate the information-theoretic performance under informed attacks. In the case of binary content fingerprinting, in a blind attack, a probe is produced at random independently from the fingerprints of the original contents. Contrarily, informed attacks assume that the attacker might have some information about the original content and is thus able to produce a counterfeit probe that is related to an authentic fingerprint corresponding to an original item, thus leading to an increased probability of false acceptance. We demonstrate the impact of the ability of an attacker to create counterfeit items whose fingerprints are related to fingerprints of authentic items, and consider the influence of the length of the fingerprint on the performance of finite-length systems. Finally, the information-theoretic achieveble rate of content identification systems sustaining informed attacks is derived under asymptotic assumptions about the fingerprint length.
{"title":"Content authentication and identification under informed attacks","authors":"F. Beekhof, S. Voloshynovskiy, F. Farhadzadeh","doi":"10.1109/WIFS.2012.6412638","DOIUrl":"https://doi.org/10.1109/WIFS.2012.6412638","url":null,"abstract":"We consider the problem of content identification and authentication based on digital content fingerprinting. Contrary to existing work in which the performance of these systems under blind attacks is analysed, we investigate the information-theoretic performance under informed attacks. In the case of binary content fingerprinting, in a blind attack, a probe is produced at random independently from the fingerprints of the original contents. Contrarily, informed attacks assume that the attacker might have some information about the original content and is thus able to produce a counterfeit probe that is related to an authentic fingerprint corresponding to an original item, thus leading to an increased probability of false acceptance. We demonstrate the impact of the ability of an attacker to create counterfeit items whose fingerprints are related to fingerprints of authentic items, and consider the influence of the length of the fingerprint on the performance of finite-length systems. Finally, the information-theoretic achieveble rate of content identification systems sustaining informed attacks is derived under asymptotic assumptions about the fingerprint length.","PeriodicalId":396789,"journal":{"name":"2012 IEEE International Workshop on Information Forensics and Security (WIFS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134115997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/WIFS.2012.6412636
Changwei Liu, A. Singhal, D. Wijesekera
Attack graphs compute potential attack paths from a system configuration and known vulnerabilities of a system. Evidence graphs model intrusion evidence and dependencies among them. In this paper, we show how to map evidence graphs to attack graphs. This mapping is useful for application of attack graphs and evidence graphs for forensic analysis. In addition to helping to refine attack graphs by using known sets of dependent attack evidence, important probabilistic information contained in evidence graphs can be used to compute or refine potential attack success probabilities obtained from repositories like CVSS. Conversely, attack graphs can be used to add missing evidence or remove irrelevant evidence trails to build a complete evidence graph. We illustrated the mapping by using a database attack as a case study.
{"title":"Mapping evidence graphs to attack graphs","authors":"Changwei Liu, A. Singhal, D. Wijesekera","doi":"10.1109/WIFS.2012.6412636","DOIUrl":"https://doi.org/10.1109/WIFS.2012.6412636","url":null,"abstract":"Attack graphs compute potential attack paths from a system configuration and known vulnerabilities of a system. Evidence graphs model intrusion evidence and dependencies among them. In this paper, we show how to map evidence graphs to attack graphs. This mapping is useful for application of attack graphs and evidence graphs for forensic analysis. In addition to helping to refine attack graphs by using known sets of dependent attack evidence, important probabilistic information contained in evidence graphs can be used to compute or refine potential attack success probabilities obtained from repositories like CVSS. Conversely, attack graphs can be used to add missing evidence or remove irrelevant evidence trails to build a complete evidence graph. We illustrated the mapping by using a database attack as a case study.","PeriodicalId":396789,"journal":{"name":"2012 IEEE International Workshop on Information Forensics and Security (WIFS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133096676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/WIFS.2012.6412660
R. Giuliano, A. Neri, Damiano Valletta
This contribution is focused on securing end-to-end unicast communications in heterogeneous sensor networks comprising satellite links, while maintaining effective network performance. The proposed protocol extends the LOCKSAT (LOCal Key Synchronization and generation for data security in sATellite communication) key management procedure, and is able to guarantee a frequent key renewal while overcoming limitations of both sensor and satellite segment. Effectiveness of the solution is assessed through a test bed including real and simulated satellite links.
这一贡献的重点是在包括卫星链路的异构传感器网络中保护端到端单播通信，同时保持有效的网络性能。该协议扩展了LOCKSAT (LOCal Key Synchronization and generation for data security in sATellite communication)密钥管理过程，能够在克服传感器和卫星段限制的同时保证密钥的频繁更新。通过包括真实和模拟卫星链路的试验台评估了该解决方案的有效性。
{"title":"End-to-end secure connection in heterogeneous networks for critical scenarios","authors":"R. Giuliano, A. Neri, Damiano Valletta","doi":"10.1109/WIFS.2012.6412660","DOIUrl":"https://doi.org/10.1109/WIFS.2012.6412660","url":null,"abstract":"This contribution is focused on securing end-to-end unicast communications in heterogeneous sensor networks comprising satellite links, while maintaining effective network performance. The proposed protocol extends the LOCKSAT (LOCal Key Synchronization and generation for data security in sATellite communication) key management procedure, and is able to guarantee a frequent key renewal while overcoming limitations of both sensor and satellite segment. Effectiveness of the solution is assessed through a test bed including real and simulated satellite links.","PeriodicalId":396789,"journal":{"name":"2012 IEEE International Workshop on Information Forensics and Security (WIFS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123480841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/WIFS.2012.6412616
Xuanbin Si, Jianjiang Feng, Jie Zhou
Elastic distortion of friction ridge skin is one of the major challenges in fingerprint matching. Since existing fingerprint matching systems cannot match seriously distorted fingerprints, criminals may purposely distort their fingerprints to evade identification. Existing distortion detection techniques require availability of specialized hardware or fingerprint video, limiting their use in real applications. In this paper we conduct a study on fingerprint distortion and develop an algorithm to detect fingerprint distortion from a single image which is captured using traditional fingerprint sensing techniques. The detector is based on analyzing ridge period and orientation information. Promising results are obtained on a public domain fingerprint database containing distorted fingerprints.
{"title":"Detecting fingerprint distortion from a single image","authors":"Xuanbin Si, Jianjiang Feng, Jie Zhou","doi":"10.1109/WIFS.2012.6412616","DOIUrl":"https://doi.org/10.1109/WIFS.2012.6412616","url":null,"abstract":"Elastic distortion of friction ridge skin is one of the major challenges in fingerprint matching. Since existing fingerprint matching systems cannot match seriously distorted fingerprints, criminals may purposely distort their fingerprints to evade identification. Existing distortion detection techniques require availability of specialized hardware or fingerprint video, limiting their use in real applications. In this paper we conduct a study on fingerprint distortion and develop an algorithm to detect fingerprint distortion from a single image which is captured using traditional fingerprint sensing techniques. The detector is based on analyzing ridge period and orientation information. Promising results are obtained on a public domain fingerprint database containing distorted fingerprints.","PeriodicalId":396789,"journal":{"name":"2012 IEEE International Workshop on Information Forensics and Security (WIFS)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122879978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/WIFS.2012.6412634
Panagiotis Andriotis, G. Oikonomou, T. Tryfonas
This paper introduces a method for acquiring forensic-grade evidence from Android smartphones using open source tools. We investigate in particular cases where the suspect has made use of the smartphone's Wi-Fi or Bluetooth interfaces. We discuss the forensic analysis of four case studies, which revealed traces that were left in the inner structure of three mobile Android devices and also indicated security vulnerabilities. Subsequently, we propose a detailed plan for forensic examiners to follow when dealing with investigations of potential crimes committed using the wireless facilities of a suspect Android smartphone. This method can be followed to perform physical acquisition of data without using commercial tools and then to examine them safely in order to discover any activity associated with wireless communications. We evaluate our method using the Association of Chief Police Officers' (ACPO) guidelines of good practice for computer-based, electronic evidence and demonstrate that it is made up of an acceptable host of procedures for mobile forensic analysis, focused specifically on device Bluetooth and Wi-Fi facilities.
{"title":"Forensic analysis of wireless networking evidence of Android smartphones","authors":"Panagiotis Andriotis, G. Oikonomou, T. Tryfonas","doi":"10.1109/WIFS.2012.6412634","DOIUrl":"https://doi.org/10.1109/WIFS.2012.6412634","url":null,"abstract":"This paper introduces a method for acquiring forensic-grade evidence from Android smartphones using open source tools. We investigate in particular cases where the suspect has made use of the smartphone's Wi-Fi or Bluetooth interfaces. We discuss the forensic analysis of four case studies, which revealed traces that were left in the inner structure of three mobile Android devices and also indicated security vulnerabilities. Subsequently, we propose a detailed plan for forensic examiners to follow when dealing with investigations of potential crimes committed using the wireless facilities of a suspect Android smartphone. This method can be followed to perform physical acquisition of data without using commercial tools and then to examine them safely in order to discover any activity associated with wireless communications. We evaluate our method using the Association of Chief Police Officers' (ACPO) guidelines of good practice for computer-based, electronic evidence and demonstrate that it is made up of an acceptable host of procedures for mobile forensic analysis, focused specifically on device Bluetooth and Wi-Fi facilities.","PeriodicalId":396789,"journal":{"name":"2012 IEEE International Workshop on Information Forensics and Security (WIFS)","volume":"7 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120910542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/WIFS.2012.6412639
Thomas Gloe
JPEG file format standards define only a limited number of mandatory data structures and leave room for interpretation. Differences between implementations employed in digital cameras, image processing software, and software to edit metadata provide valuable clues for basic authentication of digital images. We show that there exists a realistic chance to fool state-of-the-art image file forensic methods using available software tools and introduce the analysis of ordered data structures on the example of JPEG file formats and the EXIF metadata format as countermeasure. The proposed analysis approach enables basic investigations of image authenticity and documents a much better trustworthiness of EXIF metadata than commonly accepted. Manipulations created with the renowned metadata editor ExifTool and various image processing software can be reliably detected. Analysing the sequence of elements in complex data structures is not limited to JPEG files and might be a general principle applicable to different multimedia formats.
{"title":"Forensic analysis of ordered data structures on the example of JPEG files","authors":"Thomas Gloe","doi":"10.1109/WIFS.2012.6412639","DOIUrl":"https://doi.org/10.1109/WIFS.2012.6412639","url":null,"abstract":"JPEG file format standards define only a limited number of mandatory data structures and leave room for interpretation. Differences between implementations employed in digital cameras, image processing software, and software to edit metadata provide valuable clues for basic authentication of digital images. We show that there exists a realistic chance to fool state-of-the-art image file forensic methods using available software tools and introduce the analysis of ordered data structures on the example of JPEG file formats and the EXIF metadata format as countermeasure. The proposed analysis approach enables basic investigations of image authenticity and documents a much better trustworthiness of EXIF metadata than commonly accepted. Manipulations created with the renowned metadata editor ExifTool and various image processing software can be reliably detected. Analysing the sequence of elements in complex data structures is not limited to JPEG files and might be a general principle applicable to different multimedia formats.","PeriodicalId":396789,"journal":{"name":"2012 IEEE International Workshop on Information Forensics and Security (WIFS)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121580707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-12-01DOI: 10.1109/WIFS.2012.6412621
Brian DeCann, A. Ross
The matching accuracy of a biometric system is typically quantified through measures such as the False Match Rate (FMR), False Non-match Rate (FNMR), Equal Error Rate (EER), Receiver Operating Characteristic (ROC) curve and Cumulative Match Characteristic (CMC) curve. In this work, we analyze the relationship between the ROC and CMC curves, which are two measures commonly used to describe the performance of verification and identification systems, respectively. We establish that it is possible for a biometric system to exhibit “good” verification performance and “poor” identification performance (and vice versa) by demonstrating the conditions required to produce such outcomes. Experimental analysis using synthetically generated match scores confirms our hypothesis that the ROC or CMC alone cannot completely characterize biometric system performance.
{"title":"Can a “poor” verification system be a “good” identification system? A preliminary study","authors":"Brian DeCann, A. Ross","doi":"10.1109/WIFS.2012.6412621","DOIUrl":"https://doi.org/10.1109/WIFS.2012.6412621","url":null,"abstract":"The matching accuracy of a biometric system is typically quantified through measures such as the False Match Rate (FMR), False Non-match Rate (FNMR), Equal Error Rate (EER), Receiver Operating Characteristic (ROC) curve and Cumulative Match Characteristic (CMC) curve. In this work, we analyze the relationship between the ROC and CMC curves, which are two measures commonly used to describe the performance of verification and identification systems, respectively. We establish that it is possible for a biometric system to exhibit “good” verification performance and “poor” identification performance (and vice versa) by demonstrating the conditions required to produce such outcomes. Experimental analysis using synthetically generated match scores confirms our hypothesis that the ROC or CMC alone cannot completely characterize biometric system performance.","PeriodicalId":396789,"journal":{"name":"2012 IEEE International Workshop on Information Forensics and Security (WIFS)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116889228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：