User Verification Research Articles

User perspectives on the security of access data, operator handover procedures and “insult rate” for speaker verification in automated telephone services

This paper presents the results from two experiments which tested a number of important dialogue and system design issues relevant to automated telephone services with speaker verification capabilities. Those issues are: (a) User attitudes and perceived security of different security data types. (b) User attitudes towards dialogue messages for verification failure. (c) The influence of multiple rejections (“insult rate”) on user attitudes. Best strategies for completing user verification with combinations of automated systems and human telephone agents. Results show that users have strong opinions towards the above issues and consequently that speaker verification procedures in automated telephone services need to be carefully researched and designed.

Verification of computer users using keystroke dynamics

This paper presents techniques to verify the identity of computer users using the keystroke dynamics of computer user's login string as characteristic patterns using pattern recognition and neural network techniques. This work is a continuation of our previous work where only interkey times were used as features for identifying computer users. In this work we used the key hold times for classification and then compared the performance with the former interkey time-based technique. Then we use the combined interkey and hold times for the identification process. We applied several neural network and pattern recognition algorithms for verifying computer users as they type their password phrases. It was found that hold times are more effective than interkey times and the best identification performance was achieved by using both time measurements. An identification accuracy of 100% was achieved when the combined hold and intekey time-based approach were considered as features using the fuzzy ARTMAP, radial basis function networks (RBFN), and learning vector quantization (LVQ) neural network paradigms. Other neural network and classical pattern algorithms such as backpropagation with a sigmoid transfer function (BP, Sigm), hybrid sum-of-products (HSOP), sum-of-products (SOP), potential function and Bayes' rule algorithms gave moderate performance.

5557686 Method and apparatus for verification of a computer user's identification, based on keystroke characteristics : Brown Marcus E; Rogers Samuel J Tuscaloosa, AL, UNITED STATES assigned to University of Alabama

5557686 Method and apparatus for verification of a computer user's identification, based on keystroke characteristics : Brown Marcus E; Rogers Samuel J Tuscaloosa, AL, UNITED STATES assigned to University of Alabama

Automated assessment of numerical chromosomal aberrations in paraffin embedded prostate tumor cells stained by in situ hybridization.

We investigated the feasibility of automated counting of in situ hybridization signals (ISH) in interphase cells isolated from paraffin embedded prostate tissue. In total, 34 specimens from 7 patients with prostate cancer were stained with probes specific for the centromeric regions of chromosomes Y, 1, 7, 8, 10, and 15, using an immunoperoxidase based technique suitable for bright-field microscopy. Enumeration of the number of ISH spots of 500 nuclei per specimen was performed (1) using an automatic system developed without any human intervention and (2) using the same system, but including verification of the counts based on visual inspection of the stored images. As reference from each specimen, 200 cell nuclei were evaluated manually, using conventional microscopy. A typical analysis procedure (including user verification) took 35 min. The difference (root mean error) between the automated counting and the counting after visual interaction was relatively small (15%). The percentage of cells with incorrect counts by automated analysis was 20.2%, a number that could easily be improved by user interaction. Detection of cells with aneusomy proved to be more sensitive compared to the routine manual counting, in cases where aberrant frequencies were low. Automated counting of samples with low frequencies (< 10%) resulted in a higher frequency of aberrant cells in 9 of 11 cases, probably due to the fact that an unbiased cell selection is guaranteed. Automated assessment of ISH signals is considered useful for the evaluation of chromosomal aberrations in prostate tumor cells, provided that the counts are visually confirmed.

Automated assessment of numerical chromosomal aberrations in paraffin embedded prostate tumor cells stained by in situ hybridization

We investigated the feasibility of automated counting of in situ hybridization signals (ISH) in interphase cells isolated from paraffin embedded prostate tissue. In total, 34 specimens from 7 patients with prostate cancer were stained with probes specific for the centromeric regions of chromosomes Y, 1, 7, 8, 10, and 15, using an immunoperoxidase based technique suitable for bright-field microscopy. Enumeration of the number of ISH spots of 500 nuclei per specimen was performed (1) using an automatic system developed without any human intervention and (2) using the same system, but including verification of the counts based on visual inspection of the stored images. As reference from each specimen, 200 cell nuclei were evaluated manually, using conventional microscopy. A typical analysis procedure (including user verification) took 35 min. The difference (root mean error) between the automated counting and the counting after visual interaction was relatively small (15%). The percentage of cells with incorrect counts by automated analysis was 20.2%, a number that could easily be improved by user interaction. Detection of cells with aneusomy proved to be more sensitive compared to the routine manual counting, in cases where aberrant frequencies were low. Automated counting of samples with low frequencies (<10%) resulted in a higher frequency of aberrant cells in 9 of 11 cases, probably due to the fact that an unbiased cell selection is guaranteed. Automated assessment of ISH signals is considered useful for the evaluation of chromosomal aberrations in prostate tumor cells, provided that the counts are visually confirmed. © 1996 Wiley-Liss, Inc.

User verification through pointing characteristics: an exploration examination

Previous research has highlighted that all data security systems rest on the assumption of accurate user verification. Although much research has focused on speech and keystroke characteristics, no study has examined the potential of indirect cursor control devices, such as mouse or pen, as a means of personal user verification. This paper presents the result of an exploratory examination of the measurement of individual users' behaviour elicited while using two indirect input devices (puck and pen). Ten subjects undertook two series of 500 trials using the puck and pen in a counterbalanced design. Each trial involved guiding the cursor to one of ten possible targets, projected upon one of five angles of projection and one of two distances. Data recorded comprised a series of ( x, y) coordinates and associated time stamps of each component of the movement. Five parameters for each full movement were extracted-total time to reach the target, maximum velocity of the movement, maximum acceleration for the movement, time to maximum velocity of movement, time to maximum acceleration of the movement. Results of a series of Multivariate Analyses of Variance indicated that for both the puck and the pen data, there were statistically significant differences between subjects for each of the five parameters. This set of discriminating parameters was then embedded in a verification paradigm. Results indicated that the average error rates varied between 39% (S.D.=2%) and 14% (S.D.=2%) for the puck and 38% (S.D.=2%) and 12% (S.D.=2%) for the pen. Error rates were dependent upon the number of samples used when making the verification decision. This research suggests that pointing device measurements using the current parameters are not a viable method of user verification by themselves. However, with average error rates as low as 12%, it may be reasonable to integrate them into a multi-modal security system. Practical implications and future research directions are discussed.

Keyboard user verification: toward an accurate, efficient, and ecologically valid algorithm

This paper proposes new measures of individual differences in typing behaviour which provide a means of accurately verifying the identity of the typist. A first study examined the efficacy of a multivariate measure of inter-key latencies and a probabilistic discriminator statistic in conjunction with an individual filtering system which eliminates occasional disfluent keystrokes. The results indicate that, under optimum conditions but with a very small test sample, these measures lead to better typist verification than measures suggested earlier by Umphress and Williams and then Leggett and Williams. A second study validated the improved algorithm under more ecologically valid conditions and showed that when training and test sessions were separated by one week, typist verification using the new algorithm achieved combined false-acceptance and false-rejection rates of 0.9% and 3.8% for test samples of 300 and 50 digraphs respectively.

Computer verification of human users' identity: A theoretical model and some evaluation criteria

There is today a great need for reliable methods to securely verify a human computer user. Passwords are no longer sufficient in many applications. For a sound choice of an identity verification method one must be able to objectively compare the candidates. This can be accomplished only with a general description of the process which is valid for all methods and with a common way of measuring performance. This paper presents a general model of what actually happens in equipment for identity verification. It also gives criteria for good descriptions of the reliability of the equipment in terms of the possibility of a false decision.

Network security

Security in computer networks is often viewed as too expensive, but it is important. A first step in protecting a computer network is to restrict access. A product has been designed to provide secure identification of a user for access to a network, computer and data system. A system has also been developed which handles user verification, message protection and message privacy. This system is application-dependent.

System design for detection and correction of spelling errors in scientific and scholarly text

AbstractThe SPEEDCOP project recently completed at Chemical Abstracts Service (CAS) extracted over 50,000 misspellings from approximately 25,000,000 words of text from seven scientific and scholarly databases. The misspellings were automatically classified and analyzed and the results used to design and implement a program that proved capable of correcting most such errors. Analysis of the performance of the spelling error detection and correction programs highlighted the features that should be incorporated into a powerful and user‐friendly interactive system suitable for nonprogram‐mers. These include document level thresholds for misspelling detection, automatic reuse of user decisions, and user verification and control of correction. An advantage of the proposed design is that the system automatically customizes itself to its environment. This article is primarily concerned with system design, not implementation details.

Automated Signal Generator Level Characterization and Verification

Automatic test systems are described that are used to characterize and verify the output level performance of signal generators using internally stored correction data applied under microprocessor control. The characterization technique allows user verification of output level performance by direct measurement with a conventional power meter. Particular emphasis is given to a level verification system capable of measuring output power from +20 dBm to less than -140 dBm in a frequency range of 100 kHz to 2.5 GHz with an uncertainty of less than 1 dB. An analysis of error factors and actual performance data is presented.

Dipmeter Advisor Expert System: ABSTRACT

The dipmeter services offered by Schlumberger consist of measurements made in a well bore to determine the inclinations, or dip, of the bedding layers penetrated by the well. The measurements are represented on a log in the form of arrow plots, which indicate the magnitude and direction of the dip as a function of depth. Information about the underground structure and stratigraphy can be derived from arrow plot patterns on the dipmeter log in conjunction with other types of data from the borehole as well as some general knowledge of the geological area. Traditionally, interpretation of dipmeter data has been made by a human expert who identifies and decodes the arrow plot patterns. The Dipmeter Advisor system is an application of artificial intelligence and expert system techniques to dipmeter log interpretation. End_Page 1703------------------------------ It incorporates the inference and knowledge of human dipmeter experts. The first prototype system, which was completed in December 1980, consisted of interpretation in marine environments, but recently the system has been extended to continental and transitional environments as well. The Dipmeter Advisor system has a highly interactive graphics user interface. During the interpretation, the user has access to the arrow plot data and other related well data through a graphics display screen. The interpretation is made in a sequence of passes over the data, each pass arriving at some conclusions based on user input, combined with applications of the rules of dipmeter interpretation and of pattern recognition algorithms in previous passes. The partial results are displayed on the graphics screen for user verification and the user can, with graphics interaction devices, make any additions, deletions, and modifications of the results in each pass. The final output of the system consists of a log annotated much in the same way as dipmeter logs are currently annotated by human experts. Several aspects of the Dipmeter Advisor system will be described: the system organization, the graphics interface, and the general form of the rules and the inference structure. The operation of the Dipmeter Advisor system will be demonstrated with an example of dipmeter interpretation. End_of_Article - Last_Page 1704------------