Table of ContentsIntroductionBehavioral BiometricsConclusionIntroductionWith the explosion of computers and the Internet in our daily lives, the need for reliable computer security is gradually increasing. Biometric technologies provide a user-friendly and reliable control methodology for access to computer systems, networks and workplaces. The majority of research should focus on the study of well-established physical biometric data such as fingerprints or iris. Behavioral biometrics systems are generally less well established, and only those that rely largely on muscular control, such as keystrokes, steps or marks, are well analyzed. Behavioral data often does not require any special hardware and is therefore very cost-effective. Although most behavioral biometric data is not unique enough to provide reliable proof of human identity, it has been shown to provide sufficiently accurate proof of identity. Say no to plagiarism. Get a tailor-made essay on “Why Violent Video Games Should Not Be Banned”? Get an Original Essay In carrying out their daily tasks, human beings employ different plans, use different styles, and apply unique skills and knowledge. One of the defining characteristics of a behavioral biometric is the combination of the time dimension as part of the behavioral brand. The behavior measured has a beginning, a period and an end. Behavioral biometrics researchers attempt to quantify the behavioral traits revealed by users and use the resulting trait profiles to successfully verify identity. In this section, the authors provide an overview of the most recognized behavioral biometrics. Behavioral biometrics can be classified into five groups based on the type of information collected about the user. The first group is authorship-based biometric data, based on examining a section of text or a drawing made by a person. Authentication is carried out by observing the stylistic individualities typical of the author of the work under examination, such as the terminology used, punctuation or brushstrokes. The second group includes biometrics based on human-machine interaction (HCI). In their daily interaction with computers, human beings employ different approaches, use different styles, and apply unique abilities and knowledge. Researchers attempt to quantify these characteristics and use the resulting trait profiles to successfully verify uniqueness. HCI-based biometrics can be subdivided into additional groups. The first group includes human interaction with input devices such as keyboards, computer mice, and haptic systems that can record inherent, distinctive, and coherent muscle actions. The second group includes HCI-based behavioral biometrics that measure advanced human behavior such as policy, knowledge or skills demonstrated by the user while interacting with different software. The third group is closely linked to the second and constitutes all indirect HCI. event-based biometrics that can be found by indirectly monitoring the user's HCI behavior via notable low-level actions of computer software. These include system call traces, audit logs, program execution suggestions, registry access, storage activity,analysis of call stack data and system calls. Such low-level events are produced unintentionally by the user when interacting with different software. The same HCI-based biometrics are sometimes well known to different researchers under different names. IDSs based on system calls or audit logs are often classified as using program execution traces and those based on call stack data as being based on system calls. This misperception may be related to the fact that there is a high interdependence between different indirect behavioral biometrics and that they are often used in combination to improve the accuracy of the system being developed. For example, system calls and program counter data may be collective in the same behavioral mark or audit logs may contain system call information. It should also be remembered that a human being is indirectly behind each of these mirror images of behavior and therefore a high degree of connection should be expected. The fourth group of behavioral biometrics, and perhaps the best studied, relies on the motor skills of users to perform confirmation. Motor skills are a human being's ability to use their muscles. Muscle movements depend on the proper functioning of the brain, skeleton, joints and nervous system. Thus, motor skills indirectly reflect the quality of the functioning of these systems, which allows confirmation by the person. Most motor skills are learned, not inherited, with disabilities potentially affecting motor skill development. The authors accept the definition of motor skill-based behavioral biometrics, also called “kinetic,” as biometrics based on distinctive, unique, and stable muscular actions of the user while performing a particular task. The fifth and final group consists of purely behavioral biometrics. Purely behavioral biometrics measure human behavior without being directly absorbed by measurements of body parts or intrinsic, inimitable and enduring muscular movements such as the way an individual walks, types or even holds a tool. Human beings use different strategies, skills, and knowledge when presenting mentally demanding tasks. Purely behavioral biometrics measures these behavioral traits and makes successful identity confirmation possible. Behavioral biometrics1. Email Behavior: Email forwarding behavior is not the same for all individuals. Some people work nights and send masses of emails to many different addresses; others only check their mail in the morning and communicate with only one or two people. All of these features can be used to create a behavioral profile that can serve as behavioral biometrics for an individual. The length of the emails, the time of day the mail is sent, how the inbox is normally emptied, and of course the recipient addresses, among other variables, can all be collective to create a vector of basic characteristics for the person's e-mail behavior. Some work on the use of email behavior modeling has been done by Stolfo et al. They investigated the possibility of identifying the spread of a virus via email by observing anomalies in email sending behavior, such as factionunusual behavior of recipients of the same e-mail. For example, sending the same email to your girlfriend and your boss is not an everyday existence. Vel et al. (2001) applied authorship identification techniques to determine the likely author of an e-mail message. In addition to the features used in identifying authorship, the authors also used some physical features specific to email such as: the use of a salutation, a farewell acknowledgment, a signature, the number of attachments, the location of requoted text in the body of the message, the incidence of HTML tags. distribution and total number of HTML tags. In total, almost 200 features are used in the experiment, but some oft-cited features used to determine authorship are not appropriate in the email domain due to the smaller average size of these communications. .2. Audit logs. Most modern operating systems keep records of user actions and interactions with programs. While these audit trails may be of interest to behavioral intrusion detection researchers, specialized audit trails specifically aimed at security enforcement can potentially be much more powerful. A typical audit log might contain evidence such as CPU and I/O usage, number of associates of each location, whether a directory was accessed, file creation, modification of another user ID, modified audit record, system activity level, network and host. Experimentally, collecting audit events has been shown to be a less disruptive technique than recording system calls. Since a massive amount of audit data can be produced by overwhelming an intrusion detection system, it has been suggested that random sampling could be a rational approach to auditing the data. Additional data may be useful in cases of individual suspicious activity compared to normal behavior. For example, information about user status changes, new users added, terminated users, current users, or changed job obligations may be necessary to reduce the number of false positives produced by the IDS. Because a large amount of potentially valuable information can be captured by audit logs, a large number of investigators are concerned about this form of indirect HCI-based biometrics.3. Biometric sketch. Al-Zubi et al. (2003) and Brömme and Al-Zubi (2003) planned a biometric sketch confirmation method based on sketch recognition and the user's personal knowledge of the drawing content. The system asks a user to generate a simple sketch, for example of three circles, and each user is free to do it in any way that suits them. Since there are a large number of different combinations for combining several simple physical shapes, sketches from different users are unique enough to provide accurate authentication. The method measures the user's knowledge about the sketch, which is only available to the authentic old user. Features such as the location of the breezes and the comparative position of different primitives are taken as the profile of the sketch. Similar methods are tried by Varenhorst (2004) with a system called “passdoodles” as well as by Jermyn et al. (1999) with a system called “draw-a-secret”. Finally, a.