Cyber security system and method

Abstract

A cyber security system creates a behavioral framework for evaluating cyber security of computer systems of an organization based on employees of the organization.SOLUTION: The system leverages offline and online personal identity information and then converts this data into anonymous identifiers to protect privacy. The identifiers are used to retrieve data, including behavioral data, from the identity graph. A business-to-business identity graph correlates the name of the organization maintaining the targeted computer system with the anonymous identifier of the employee. Online activity is collected by pixels fired from a website accessed by a user browser and collected by one or more remote servers.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] This application claims the benefit of U.S. Provisional Patent Application No. 62 / 991,672, entitled "Cyber ​​Security System," filed March 19, 2020. The above application is incorporated herein by reference in its entirety. [Background technology]

[0002] "Phishing" attacks are a form of social engineering. Typically, individuals involved in such attacks send emails or other electronic messages with the goal of fraudulently enticing recipients to disclose private information, such as passwords or financial data. The sender of the message often poses as a trustworthy person or entity, such as an executive at the target's employer or a financial institution. Often, the message contains a link to a website, which may look very similar to a legitimate site in order to trick the recipient into submitting private information. In other cases, the link may lead to a website that automatically installs malware on the target's personal computing device. Because the goal of a phishing attack is to trick the recipient into voluntarily disclosing private information, phishing attacks do not initially require the attacker to actually breach security measures put in place by the recipient's computer system or network. If the information disclosed in this way includes a password, the attacker can then use the fraudulently obtained information to access the recipient's computer system. Once access is gained, the attacker can steal private information, install malware, or engage in ransomware attacks.

[0003] Attempts to eliminate phishing attacks in businesses generally involve technical solutions or employee education efforts. Technical solutions may include, for example, warning messages that appear in emails from external senders, with the purpose of highlighting messages that may appear to be from an organization's employees, such as supervisors or IT personnel, but that actually originate from another source. However, email systems were not designed with these types of attacks in mind, and therefore there is no complete technical solution to the problem. Another approach is for computer system administrators to launch their own phishing attacks and flag users of the system who are fooled by the attack for additional training. Many organizations require all employees to receive at least some level of training in identifying phishing attacks and other cybersecurity risks, such as annual training requirements. However, while employee education efforts may reduce the likelihood that an individual employee can be fooled by a phishing attack, an attacker only needs to trick a single person to obtain desired information, and therefore the risk of failure increases proportionally to the number of employees with access to the organization's computer network. It would be desirable to provide a technical system capable of identifying employees who are most likely to be at risk from phishing attacks and assessing the risk to the organization as a whole so that a response proportionate to the threat the organization faces can be prepared.

[0004] The statements made in this background section are not admitted to be prior art with respect to the present invention. Summary of the Invention

[0005] In some implementations, the present invention is directed to systems and methods for providing a quantifiable measure of the risk that any particular group of users of a computer system (such as employees at a large company or other organization) represents in the event of a phishing attack directed at one or more of those users. Systems for implementing the present invention utilize one or more identity graphs. An identity graph is a large data structure containing identifiers that are matched to entities, such as consumers and businesses. Identity graphs typically contain much additional information associated with the identifiers, such as personal information, demographic information, firmographic information, propensity, or consumption data.

[0006] In some implementations, a system for implementing the present invention may utilize an offline identity graph (i.e., an identity graph with offline personal and consumption data, such as in-store purchases), an online identity graph (i.e., an identity graph with online data, such as online purchases, browsing history, and email addresses), and a business-to-business (B2B) identity graph (i.e., a graph with data used for business-to-business commerce, rather than between businesses and end consumers). The method utilizes offline and online identity information (such as personally identifiable data or PII) about target users and then converts this data into anonymous identifiers to protect the privacy of these individuals. The anonymous identifiers are generated in a manner that does not include PII and does not allow PII to be derived from the anonymous identifiers. The anonymous identifiers are generated through a transformation process that converts PII into pseudonymous identifiers and connects the pseudonymous identifiers to other online or anonymous signals about the individuals, such as those found in the online identity graph. This online identity graph can also link anonymous identifiers to other behavioral data from a marketplace of data providers, including but not limited to psychographic, demographic, and behavioral data.

[0007] In another implementation, a passive view is provided through a B2B identity graph, which passively and automatically translates the names of organizations maintaining targeted computer systems with anonymous identifiers of employees or other users associated with those organizations. The B2B identity graph includes nodes that each correspond to a business entity and may include a substantially comprehensive set of nodes for business entities within a particular segment in a particular geographic or legal region. Online activity is collected by pixels fired from websites accessed by the user browser and aggregated by one or more remote servers. By combining online and offline activity and matching it to individuals (via anonymous identifiers), the system can create a behavioral framework for individual users of a computer system without compromising the privacy of those individuals and without disclosing personal information about the users to computer system administrators. Using the identified behavioral traits, implementations then calculate risk factors associated with individual users and for the computer system as a whole. Further, by aggregating such data for several organizations' computer systems, implementations may provide a comparative measure of the cyber risk faced by one organization compared to the cyber risk faced by other organizations, including, for example, organizations in a similar sector, organizations of a similar size, organizations in the same legal jurisdiction, or any other means by which a company may be segmented.

[0008] In some implementations, the present invention enables computer network administrators to understand their system's level of risk to cybersecurity issues, such as phishing attacks, insider threats, or other related tactics. It may also enable administrators to restrict certain access or features accessible to certain users to reduce the risk of such attacks on the computer network. Similarly, the present invention allows administrators, or other stakeholders such as cyber insurance providers or corporate partners, to gain a better overall sense of the risk of successful phishing attacks on computer networks in general by knowing the risk posed by specific users of the system rather than by computer users as a whole, thereby allowing appropriate safety measures to be implemented corresponding to the level of risk. Administrators can act based on this knowledge, for example, by creating targeted training for high-risk users. The present invention can also serve as a data point in cyber risk assessments around phishing and cybersecurity culture. Assessing these attributes using traditional methods is extremely time-consuming because it relies on inefficient communication between the assessing company and the vendor being assessed. Additionally, traditional methods also rely on subjective data points automatically asserted by target companies through a questionnaire process. When the system relies on data assets such as B2B identity graphs and behavioral framework algorithms, unbiased insights into these cyber risk metrics can be generated instantly and continuously for security administrators to receive reports and differentiate between cyber threats. Various implementations of the present system and method represent a significant improvement in turnaround time from current methods in the cyber risk industry, which can take anywhere from a month to a quarter to generate results, by which time a breach may already have occurred before any action can be taken.

[0009] These and other features, objects and advantages of the present invention will become better understood upon consideration of the following detailed description of the preferred embodiments and the appended claims, taken in conjunction with the included drawings. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is an overall system architecture diagram according to one implementation of the present invention. [Figure 2] FIG. 1 is an architectural diagram for a partner platform according to one implementation of the present invention. [Figure 3] FIG. 2 is an architecture diagram for a DNS platform according to one implementation of the present invention. [Figure 4] FIG. 1 is an architectural diagram for a behavioral data platform according to one implementation of the present invention. [Figure 5] 1 is an architecture diagram for an identity platform according to one implementation of the present invention. [Figure 6] FIG. 1 is an architectural diagram of a scoring platform according to one implementation of the present invention. [Figure 7] 1 is a high-level flow diagram for a scoring platform according to one implementation of the present invention. [Figure 8] 1 is a flow diagram for the company view component of the scoring platform in accordance with one implementation of the present invention. [Figure 9] 10 is a flow diagram for the segment selection component of the scoring platform in accordance with one implementation of the present invention. [Figure 10] 1 is a flow diagram for the trait weighting component of the scoring platform, according to one implementation of the present invention. [Figure 11] 10 is a flow diagram for the behavioral bucket weighting component of the scoring platform in accordance with one implementation of the present invention. [Figure 12]1 is a flow diagram for the final score calculation component of the scoring platform according to one implementation of the present invention. [Figure 13] 1 is a flow diagram for the scoring normalization and transformation component of the scoring platform according to one implementation of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0011] Before the present invention is described in further detail, it is to be understood that the invention is not limited to the particular embodiments described, and that the terminology used in describing particular embodiments is for the purpose of describing those particular embodiments only, and is not limiting, since the scope of the invention is limited only by the claims.

[0012] Referring to FIG. 1, a system and method according to one implementation of the present invention can be described. An identity platform 10 includes hardware and software operable to match employee data files with various other data collected about employees related to cybersecurity risk. Information needed for the identity service provider is collected from various components of a partner platform 12, including servers maintained by various companies and their employees using the service, who operate through their various electronic devices, such as desktop computers and smartphones. Additionally, information is provided across the Internet from a domain name service (DNS) server in a DNS platform 16 regarding web browsing activity. Furthermore, a behavioral data platform 18 provides behavioral data to the identity platform 10. A cybersecurity score platform 14 utilizes anonymized information from the identity platform 10 to generate a cybersecurity score. This score may be continually updated using future provision of feedback data from partner platform 12 in response to previous scores calculated by scoring platform 14, which may then result in the generation of updated scores by scoring platform 14.

[0013] Referring now to FIG. 2, the partner platform 12 can be described in more detail. While only one partner platform 12 is shown herein, it should be understood that the present invention can be used with any number of partner platforms 12. Indeed, the present invention is contemplated for use with many partner platforms 12, each of which can independently utilize the cybersecurity risk scoring provided by the present invention. Employees of these companies possess various personally identifiable information (PII), such as names, physical addresses, phone numbers, and email addresses. This information is known to the companies and stored in the partner PII database 106. At the same time, employees using various digital devices (either while engaging with their employer's company or otherwise) are generating digital information through activities such as web browsing. This activity can be associated with individual employees through means such as cookies set on the employee's browser, an IP address associated with the employee, or a mobile device identifier (Mobile ID). Personal data may be received from employee-operated electronic devices, such as smartphones 102 and personal computers 104. This information is provided through the partner network 100, which is in electronic communication with the partner PII database 106. Additionally, IP / cookie information is provided to the identity platform 10 from the personal computer 104. Similarly, IP / cookie / mobile ID data is provided to the identity platform 10 from the smartphone 102. Device behavior data from these sources is provided to the behavioral data platform 18. The partner network 100 provides firmographic data to the behavioral data platform 18.Firmographic data includes, for example, information on an organization's size, revenue, industry, and business locations, which allows the company to be divided into meaningful segments for various purposes.

[0014] As shown in Figure 3, DNS servers 200 operating within the Internet framework process IP data and provide the data to corporate IP data providers. A DNS platform 16 provides the ability to convert human-readable domain names into Internet Protocol (IP) addresses used by computers for addressing activities on the Internet. While three DNS servers 200 are shown, it will be understood that the Internet backbone includes many DNS servers. IP Data Provider Servers 202306 receives DNS data and outputs IP data that is used by the identity platform 10.

[0015] 4 shows the computing components for behavioral data platform 18 in more detail. There are multiple third-party sources of data that are supplied to behavioral data provider server 306. These include modeled data (i.e., data inferred from known data based on behavioral models) from modeled data database 300, qualitative data from qualitative data database 302, and survey-based data (including data collected from user surveys as well as other sources, such as, but not limited to, warranty registrations) from survey-based data database 304. This raw behavioral data is sent to behavioral data provider server 306 for processing. Behavioral data provider server 306 then outputs the behavioral data to identity platform 10.

[0016] Additionally, the behavioral data provider server 306 may maintain a database of data relating to employees of one or more firms and associated with each such employee, which may be an identifier or “link” that is unique to such employee across the universe of all possible employees. This link is used to uniquely identify an employee despite possible ambiguity regarding names, addresses, or other such identifying information. This link may be generated so that it is anonymous, i.e., so that PII is not disclosed by the non-PII data associated with the link itself. The behavioral data provider server 306 may provide these anonymous links along with the behavioral data that it sends to the identity platform 10 to help identify the corresponding employee for matching purposes.

[0017] Referring now to FIG. 5, the hardware / software computing components of identity platform 10 may be described. These components include employee identity compute cluster 402, behavioral identity compute cluster 404, and pixel services cluster 400. Each of these clusters may consist of, for example, multiple computing platforms with multiple linked databases embedded therein. Employee identity compute cluster 402 receives PII data from partner platform 12 and uses this data for identity resolution purposes for employees. Behavioral identity compute cluster 404 receives behavioral data from behavioral data platform 18 and uses this data for the purpose of associating employees' behavioral characteristics with their resolved identities provided by employee identity compute cluster 402. Pixel services compute cluster 400 receives digital data, including device data, from employees, as well as information indicative of employees' web browsing, from partner platform 12. This may include, for example, data gathered from tracking web beacons / pixels in web pages visited by the employee and information gathered from cookies set on the employee's browser. Through communication between the employee identity compute cluster 402, behavioral identity compute cluster 404, and pixel services compute cluster 400, all of the corresponding data is matched to the employee. Once PII is used for identification and matching purposes, the employee identity compute cluster 402 strips all PII and assigns an anonymous identifier to each record of data corresponding to the employee to protect the employee's privacy. PII is not transmitted outside of the identity platform 10, and therefore there is no risk of loss of privacy due to data being intercepted in transit across a communications network.

[0018] Identity platform 10 may further include, for example, a business-to-business (B2B) identity graph 406 in communication with behavioral identity compute cluster 404. B2B identity graph 406 may include multiple logical nodes, each corresponding to a business entity, with a node present for substantially all business entities in a segment within a particular region. By utilizing B2B identity graph 406, behavioral identity compute cluster 404 is configured to perform identity resolution for multiple businesses by comparing data received at intercommunicating components of identity platform 10 against B2B identity graph 406.

[0019] 6, the components of the scoring platform 14 may be described. A risk scoring compute cluster 500 receives input from the pixel services compute cluster 400, the employee identity compute cluster 402, and the behavioral identity compute cluster 404. This information includes employee information that has been collected, filtered, matched, and consolidated through previous parts of the process. The risk scoring system cluster 500 then uses this data to generate a cybersecurity score for the organization and an accompanying report.

[0020] To generate the employee-enterprise identity graph, the system draws connections between the name of a company / organization and its associated IP addresses. The system then determines which individual identities or "employees" are significantly associated with that IP address. The resulting graph can incorporate PII, online identifiers, and / or offline identifiers and convert them into pseudonymous identifiers, which are then linked to IP addresses. If the IP address belongs to a corporate entity and the user is significantly correlated with the corporate IP, the individual is classified as an employee. These connections are then consolidated to form a single view of the organization and anonymous individuals, and their associated behavioral segments are identified. Relevant segments from the behavioral data are then selected for scoring, either by string matching the segment's name against a database of selected segments determined to be associated with cyber risk, or by performing natural language processing (NLP) modeling on the name itself.

[0021] Organizations with fewer than five anonymous identifiers associated with them are sanitized from the database for privacy purposes and not further processed. The segment ratio used to determine the final cyber risk score is calculated by determining the number of anonymous identifiers for an organization in that particular segment divided by the total number of anonymous identifiers associated with that organization. Segment grouping is then performed by applying negative and positive multiplicative weights to all ratios depending on the segment's alignment with secure or non-secure cyber practices. These segments and their corresponding ratios are then grouped into the following cyber risk traits: financial risk-taking, social risk-taking, recreational risk-taking, conscientiousness, neuroticism, openness, agreeableness, extraversion, and decision-making via string matching against a key-value database of segment and trait pairs or via clustering (i.e., principal component analysis). A trait score is then calculated by performing a weighted sum on the relevant segment ratios. In this score calculation, these weights are determined by performing feature importance and are continuously improved through a feedback loop. Traits and their corresponding trait scores are then categorized into the following behavioral buckets: decision-making, personality, and risk propensity, via string matching with key-value database trait and behavior pairs or via clustering. The overall behavior score is calculated by performing a weighted sum over the trait scores.

[0022] In the score calculation just described, weights are determined by feature importance and continuously improved via feedback loop 504. These trait scores are then pushed through another weighted sum and weights determined by performing feature importance and continuously improved via feedback loop 504 to calculate an overall risk score in risk scoring compute cluster 500. These scores are then normalized against a baseline group of companies that is sampled periodically to calculate a z-score. The z-score is scaled to a thousand point model to produce a final cybersecurity score and report 502.

[0023] With reference to Figures 7-13, the flow for processing in the risk scoring compute cluster 500 may now be described in more detail. The first step of processing occurs in a company view process 600, the substeps of which are shown in more detail in Figure 8. A build company view substep 700 takes information from the employee portal and pixel service, as previously described, to create a single view of the organization and the anonymous individuals associated with the organization (e.g., employees of the organization). In an augment company view substep 702, behavioral data is attached to the anonymous individuals through identity resolution, providing the scoring mechanism with a complete view of the organization's employee behaviors needed to assemble a cyber risk score and report 502.

[0024] Segment selection then occurs in segment selection process 602, the substeps of which are shown in more detail in FIG. 9. In various implementations of the present invention, either of two different segment selection methods may be used, or the system may implement both and provide selection 800 during segment selection. Segment string matching 802 determines which segments to assess by performing string matching against a configured list of segments associated with cyber risk. Alternatively, NPL modeling 804 determines which segments to assess through a natural language processing (NLP) model of words associated with the segment risk. In either case, scanning substep 612 from feedback 504 is used to input other "truth sets," such as email breach data sets. These are input through scanning and / or application programming interface (API) calls. After the segments for assessment are selected, processing moves to sanitation substep 806, which is used to remove organizations that do not have enough information to be categorized. In segment ratio substep 808, the ratio of the number of anonymous identifiers with each segment to the number of anonymous identifiers across the organization is calculated. Finally, in segment grouping substep 810, grouping is performed on the segments by applying negative and positive multiplicative weights to all segments depending on the segment's alignment with secure and non-secure conventions.

[0025] Trait weighting then occurs in trait weighting process 604, the substeps of which are shown in more detail in FIG. 10. In various implementations of the present invention, either of two different trait creation methods may be used, or the system may implement both and provide selection 900 during trait creation. In trait string matching 902, the system determines which segments fall into which trait groups by string matching against a database of key-value pairs. Alternatively, in trait clustering 904, principal components analysis (PCA) is used to perform clustering to group segments into broader trait categories or groups. In either case, the trait groups in one implementation of the present invention are as follows: financial risk-taking, social risk-taking, recreational risk-taking, conscientiousness, neuroticism, openness, agreeableness, extraversion, and decision-making. Processing then moves to trait feature importance substep 906, where the system determines segment weights for cyber risk calculations via feature importance. Using feature importance iterations 614, the process in this substep is continuously improved through a feedback loop. Feature importance iterations 614 iterate on weights and feature importance through a feedback loop of scored organizational risk incidents. Finally, in trait score calculation substep 908, a trait score is calculated through a weighted sum of segment ratios and corresponding importance weights.

[0026] Next, behavioral bucket weighting occurs in behavioral bucket weighting process 606, the substeps of which are shown in more detail in FIG. 11. In various implementations of the present invention, either of the two bucket weighting methods may be used, or the system may implement both and provide a selection at bucket weighting 1000. In bucket string matching 1002, the system determines which traits are in which behavioral groups by string matching against a database of key-value pairs. Alternatively, in bucket clustering 1004, the system performs clustering via PCA to group traits into broader behavioral categories. In either case, in one implementation of the present invention, the behavioral buckets are as follows: risk propensity, decision-making, and personality. The process then moves to a bucket feature importance substep 1006, where the system determines trait weights for score calculation via feature importance. Using feature importance iterations 614, the process in this substep is continuously improved through a feedback loop. Finally, the process moves to a bucket score calculation substep 1008, where the system calculates a behavior score through a weighted sum of trait scores and corresponding importance weights.

[0027] Final score calculation then occurs in final score calculation process 608, the substeps of which are shown in more detail in FIG. 12. In calculate feature importance substep 1100, the system determines behavioral category weights for score calculation via feature importance. Using feature importance iteration 614, the process in this substep is continuously improved through a feedback loop. Processing then moves to final score calculation substep 1102, where the system calculates a final cyber risk score through a weighted sum of the behavioral scores and the corresponding importance weights.

[0028] Next, normalization and transformation occur in normalization and transformation process 610, the substeps of which are shown in more detail in FIG. 13. In sample baseline group 1200, the system periodically samples organizations across sizes and industries to determine a baseline risk level for each trait and behavior bucket to scale. This substep uses input from update baseline 616, i.e., the feedback portion of 504, which updates based on, for example, employee turnover, contractor mix, and behavioral changes. Based on feedback received from participating organizations using the system, the baseline will adapt and change over time. Next, in z-score calculation substep 1202, the system calculates a z-score for the baseline group. In statistics, a "z-score," or standard score, is the number of standard deviations a raw score value is above or below the mean value of what is being measured. Raw scores above the mean have a positive z-score, while raw scores below the mean have a negative z-score. After calculating the z-scores, the system in this substep sets an interval based on the distribution of the z-scores and forces outliers that fall outside the z-score interval to either the minimum or maximum value. Finally, in scaling substep 1204, the system scales the z-scores to a specific model, in one implementation using a 1000-point model. The output of this substep is then scores and reports 502, as previously described. Scaling substep 1204 also sends its data back to feedback 504, specifically to update baseline substep 616, to create the feedback loop needed to constantly improve the baseline.

[0029] Referring again to FIG. 6 , the cybersecurity scores and reports 502 generated in the risk scoring compute cluster 500 are sent back to the partner platform 12, where they are operated and maintained by the organization desiring the scores and reports 502. The organization may then use the partner platform 12 to provide feedback, additional attributes, real-world events related to the cybersecurity risk scores and reports, qualitative input, and other data related to specific employees or the organization as a whole (collectively, feedback 504). This feedback 504 data is then provided in a feedback loop from the partner platform 12 to the cybersecurity risk scoring compute cluster 500 to update the cybersecurity scores and reports 502 using this additional information. In some implementations, any or all of these processes may occur in real time. By using real-time operation, the cybersecurity scores and reports 502 may be constantly updated to provide the most recent and accurate data. Real-time may mean, for example, that as data is received from the partner platform 12, the scores and reports 502 are constantly being recreated, updated, and resent back to the partner platform 12, even as new data is received at the scoring platform 14. In this way, for example, browsing activity by an employee that would indicate a risk could result in an adjustment to the scores and reports 502 very rapidly, even while the employee is potentially still engaged in the browsing activity that created the risk that led to the change in the scores and reports 502.

[0030] The systems and methods described herein may be implemented by any combination of hardware and software in various embodiments. For example, in one embodiment, the systems and methods may be implemented by a set of computer systems, each of which includes one or more processors that execute program instructions stored on a computer-readable storage medium coupled to the processors. The program instructions may implement the functions described herein. The various systems and displays described herein, as illustrated in the figures, represent example implementations. The order of any method may be changed, and various elements may be added, modified, or omitted.

[0031] The computing systems or computing devices described herein may implement the hardware portion of a cloud computing system or a non-cloud computing system, forming part of various implementations of the present invention. The computing system may be any of a variety of types of devices, including, but not limited to, a commodity server, a personal computer system, a desktop computer, a laptop or notebook computer, a mainframe computer system, a handheld computer, a workstation, a network computer, a consumer device, an application server, a storage device, a telephone, a mobile phone, or generally any type of computing node, compute node, compute device, and / or computing device. The computing system includes one or more processors (which may include multiple processing cores, any of which may be single- or multi-threaded) coupled to system memory via an input / output (I / O) interface. The computing system may further include a network interface coupled to the I / O interface.

[0032] In various embodiments, the computer system may be a single-processor system including one processor or a multiprocessor system including multiple processors. The processor may be any suitable processor capable of executing computing instructions. For example, in various embodiments, the processor may be a general-purpose processor or an embedded processor implementing any of a variety of instruction set architectures. In a multiprocessor system, each of the processors may typically, but not necessarily, implement the same instruction set. The computer system also includes one or more network communication devices (e.g., network interfaces) for communicating with other systems and / or components across a communications network, such as a local area network, a wide area network, or the Internet. For example, a client application executing on a computing device may use a network interface to communicate with a server application executing on a single server or on a cluster of servers implementing one or more of the components of the systems described herein in various subsystems, in a cloud computing or non-cloud computing environment. In another example, an instance of a server application executing on a computer system may use a network interface to communicate with other instances of the application, which may be implemented on other computer systems.

[0033] A computing device also includes one or more persistent storage devices and / or one or more I / O devices. In various embodiments, the persistent storage device may correspond to a disk drive, a tape drive, solid-state memory, other mass storage device, or any other persistent storage device. A computer system (or a distributed application or operating system running thereon) may store instructions and / or data in the persistent storage device as desired and retrieve the stored instructions and / or data as needed. For example, in some embodiments, a computer system may implement one or more nodes of a control plane or control system, and the persistent storage may include SSDs attached to the server nodes. Multiple computer systems may share the same persistent storage device or may share a pool of persistent storage devices, where the devices in the pool represent the same or different storage technologies.

[0034] A computer system includes one or more system memories that can store code / instructions and data accessible by the processor(s). System memory can include, for example, multiple levels of memory and memory caches in systems designed to swap information in memory based on access speed. Interleaving and swapping can extend to persistent storage in virtual memory implementations. Technologies used to implement memory can include, by way of example, static random-access memory (RAM), dynamic RAM, read-only memory (ROM), nonvolatile memory, or flash-type memory. As with persistent storage, multiple computer systems can share the same system memory or can share a pool of system memory. One or more system memories can contain program instructions executable by the processor(s) to implement the routines described herein. In various embodiments, the program instructions may be encoded in binary, assembly language, any interpreted language such as Python, a compiled language such as C / C++, or any combination thereof, and the particular languages ​​given herein are illustrative only. In some embodiments, the program instructions may implement multiple separate client, server nodes, and / or other components.

[0035] In some implementations, the program instructions may include executable instructions to implement an operating system (not shown), which may be any of a variety of operating systems, such as UNIX, LINUX, Solaris, MacOS, or Microsoft Windows. Any or all of the program instructions may be provided as a computer program product or software, which may include a non-transitory computer-readable storage medium having stored thereon instructions that can be used to program a computer system (or other electronic device) to perform a process according to various implementations. A non-transitory computer-readable storage medium may include any mechanism for storing information in a form (e.g., software, processing application) readable by a machine (e.g., a computer). Generally, a non-transitory computer-accessible medium may include a computer-readable storage medium or memory medium, such as a magnetic medium or optical medium, e.g., a disk or DVD / CD-ROM coupled to a computer system via an I / O interface. Non-transitory computer-readable storage media may include any volatile or non-volatile media, such as RAM or ROM, that may be included as system memory or another type of memory in some embodiments of a computer system. In other implementations, program instructions may be communicated using optical, acoustic, or other forms of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.) conveyed over a communications medium, such as a network and / or wired or wireless link, such as may be implemented via a network interface. The network interface may be used to interface with other devices, which may include other computer systems or any type of external electronic device.Generally, system memory, persistent storage, and / or remote storage accessible on other devices through a network may store data blocks, replicas of data blocks, metadata associated with the data blocks and / or their state, database configuration information, and / or any other information usable in implementing the routines described herein.

[0036] In some implementations, the I / O interface may coordinate I / O traffic between the processor, system memory, and any peripheral devices in the system, including through a network interface or other peripheral interface. In some embodiments, the I / O interface may perform any necessary protocol, timing, or other data conversions to convert data signals from one component (e.g., system memory) into a format suitable for use by another component (e.g., processor). In some embodiments, the I / O interface may include support for devices attached through various types of peripheral buses, such as variations on the Peripheral Component Interconnect (PCI) bus standard or the Universal Serial Bus (USB) standard. Also, in some embodiments, some or all of the functionality of the I / O interface, such as the interface to system memory, may be incorporated directly into the processor(s).

[0037] A network interface may, for example, enable data to be exchanged between the computer system and other devices attached to the network, such as other computer systems (which may implement one or more storage system server nodes, primary nodes, read-only nodes, and / or database system clients described herein). Additionally, an I / O interface may enable communication between the computer system and various I / O devices and / or remote storage. Input / output devices, in some embodiments, may include one or more display terminals, keyboards, keypads, touchpads, scanning devices, voice or optical recognition devices, or any other device suitable for entering or retrieving data with one or more computer systems. These may be directly connected to a particular computer system or may generally connect to multiple computer systems in a cloud computing environment, grid computing environment, or other system involving multiple computer systems. Multiple input / output devices may be in communication with the computer system or may be distributed across various nodes of a distributed system that includes the computer system. The user interfaces described herein may be visible to a user using various types of display screens, which may include CRT displays, LCD displays, LED displays, and other display technologies. In some implementations, input may be received through a display using touchscreen technology, while in other implementations, input may be received through a keyboard, mouse, touchpad, or other input technology, or any combination of these technologies.

[0038] In some embodiments, similar input / output devices may be separate from the computer system and may interact with one or more nodes of a distributed system that includes the computer system through a wired or wireless connection, such as over a network interface. The network interface may typically support one or more wireless networking protocols (e.g., Wi-Fi / IEEE 802.11 or another wireless networking standard). The network interface may support communication over any suitable wired or wireless general data network, such as, for example, other types of Ethernet networks. Furthermore, the network interface may support communication over a telecommunications / telephony network, such as an analog voice network or a digital fiber communications network, a storage area network, such as a Fibre Channel SAN, or any other suitable type of network and / or protocol.

[0039] Any of the distributed system embodiments described herein, or any of their components, may be implemented as one or more network-based services in a cloud computing environment. For example, read-write and / or read-only nodes in the database tier of a database system may present database services and / or other types of data storage services employing the distributed storage system described herein to clients as network-based services. In some embodiments, a network-based service may be implemented by software and / or hardware systems designed to support interoperable machine-to-machine interaction over a network. A web service may have an interface described in a machine-processable format, such as Web Services Description Language (WSDL). Other systems may interact with the network-based service in a manner prescribed by the network-based service's interface description. For example, a network-based service may define various operations that other systems can invoke and may define specific application programming interfaces (APIs) that other systems may be expected to follow when requesting the various operations.

[0040] In various embodiments, network-based services may be requested or invoked through the use of messages containing parameters and / or data associated with a network-based service request. Such messages may be formatted according to a particular markup language, such as Extensible Markup Language (XML), and / or may be encapsulated using a protocol, such as Simple Object Access Protocol (SOAP). To perform a network-based service request, a network-based service client may assemble a message containing the request and communicate the message to an addressable endpoint (e.g., a Uniform Resource Locator (URL)) corresponding to the web service using an Internet-based application layer transport protocol, such as Hypertext Transfer Protocol (HTTP). In some embodiments, network-based services may be implemented using Representational State Transfer (REST) ​​techniques rather than message-based techniques. For example, a network-based service implemented according to REST techniques may be invoked through parameters contained within an HTTP method, such as PUT, GET, or DELETE.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Although methods and materials similar or equivalent to those described herein can also be used in the practice or testing of the present invention, a limited number of exemplary methods and materials are described herein. It will be apparent to those skilled in the art that many more modifications are possible without departing from the inventive concepts herein.

[0042] All terms used herein should be interpreted in the broadest possible manner consistent with the context. When groupings are used herein, all individual members of the group and all possible combinations and subcombinations of the group are intended to be individually included in the disclosure. All references cited herein are incorporated by reference to the extent that they are not inconsistent with the present disclosure. When ranges are used herein, all points within the range and all subranges within the range are intended to be included in the disclosure.

[0043] The present invention has been described in terms of certain preferred and alternative implementations that are intended to be examples only and not limitations on the full scope of the invention.

Claims

1. A cyber security system, comprising:

1. An identity compute cluster, comprising: the identity compute cluster performing identity resolution for a plurality of objects; removing all personally identifiable information (PII) from the risk behavior data for the object; Associating a link containing no personally identifiable information with each of said objects having data related to risk behavior; an identity compute cluster configured to output data related to risk behavior for the objects and to add the link to corresponding data related to risk behavior for each of the objects; 1. A pixel services compute cluster, comprising: the pixel services compute cluster receiving online activity data from a plurality of sources; associating the online activity data with a particular online computing device; and outputting the online activity data associated with a particular online computing device to the identity compute cluster.

1. A behavioral identity compute cluster, comprising: the behavioral identity compute cluster receiving behavioral data; associating the behavioral data with a particular entity; and outputting behavioral data associated with a particular entity to the identity compute cluster; 1. A risk scoring compute cluster comprising: a risk scoring compute cluster receiving the data related to risk behavior for the object from the identity compute cluster; calculating trait scores for a plurality of cyber risk traits including at least financial risk taking, social risk taking, recreational risk taking, conscientiousness, and decision-making; grouping the trait scores into behavioral buckets including at least risk propensity, decision making, and personality; calculating a behavioral bucket score by performing a weighted sum of the trait scores within each behavioral bucket; calculating a cybersecurity score based on a weighted sum of the behavioral bucket scores; a risk scoring compute cluster configured to: A cyber security system comprising:

2. 10. The cybersecurity system of claim 1, wherein the risk scoring compute cluster is further configured to receive feedback from an enterprise computing system and to utilize the feedback to recalculate the cybersecurity scores and reports.

3. 3. The cybersecurity system of claim 2, wherein the risk scoring compute cluster is further configured to recalculate the cybersecurity scores and reports in real time.

4. 10. The cybersecurity system of claim 1, further comprising a business-to-business (B2B) identity graph, wherein the identity compute cluster is configured to perform identity resolution for the plurality of objects by comparing data received at the identity compute cluster with the B2B identity graph.

5. 5. The cybersecurity system of claim 4, wherein the B2B identity graph comprises a plurality of nodes, each node corresponding to a business entity, and there is a node for every business entity in a segment within a particular region.

6. 10. The cybersecurity system of claim 1, further comprising: a behavioral data platform configured to provide behavioral data to the behavioral identity compute cluster.

7. 10. The cybersecurity system of claim 1, further comprising a partner platform, the partner platform comprising a set of records each relating to a particular object associated with an entity, each record comprising personally identifiable information (PII) associated with the particular object, the partner platform configured to provide internet protocol (IP) address data to the pixel services compute cluster.

8. 8. The cybersecurity system of claim 7, wherein the partner platform comprises a plurality of employee electronic devices, the employee electronic devices comprising a web browser, the web browser configured to send browsing data to the pixel services compute cluster and further associate the online activity data with a particular online computing device.

9. 1. A method for assessing cybersecurity of a partner platform, comprising: creating, in the partner platform, a set of records each relating to a particular object associated with one of a plurality of entities, each record comprising personally identifiable information (PII) associated with the particular object; performing identity resolution for a plurality of entities in an identity compute cluster; and outputting data related to risk behavior for the entities; receiving, at a pixel services compute cluster, a set of internet protocol (IP) address data from the partner platform; matching online activity data from multiple sources to a particular electronic device; and outputting the online activity data associated with the particular electronic device to the identity compute cluster; matching, at a behavioral identity compute cluster, behavioral data with a particular entity of the plurality of entities; and outputting behavioral data associated with the particular entity to the identity compute cluster; In a risk scoring compute cluster, matching the behavioral data with a list of segments associated with cyber risks; clustering the segments, including at least financial risk taking, social risk taking, recreational risk taking, conscientiousness, and decision-making, into trait categories, including at least risk propensity, decision-making, and personality, and performing a weighted sum of the trait categories to calculate a cyber security score from the behavioral data associated with the particular entity; A method comprising:

10. 10. The method of claim 9, further comprising generating feedback at the partner platform and utilizing the feedback to recalculate the cybersecurity score.

11. The method of claim 10 , wherein the step of recalculating the cyber security score is performed in real time.

12. 10. The method of claim 9, further comprising the steps of: stripping all personally identifiable information (PII) from the data related to risk behavior for the objects; associating links with each of the objects with data related to risk behavior; and attaching the links to corresponding data related to risk behavior for each of the objects.

13. 10. The method of claim 9, further comprising: performing identity resolution for the plurality of objects by comparing data received at the identity compute cluster with a business-to-business (B2B) identity graph.

14. 10. The method of claim 9, further comprising transmitting browsing data from a web browser to the pixel service compute cluster to further associate the online activity data with a particular electronic device.

15. 10. The method of claim 9, wherein the matching at the risk scoring compute cluster comprises string matching to identify segments associated with cyber risks.

16. 10. The method of claim 9, wherein the matching in the risk scoring compute cluster comprises: performing natural language processing (NLP) to identify segments associated with cyber risk; and clustering the segments into the trait categories using principal component analysis (PCA).

17. 1. A system for managing cyber risk, comprising: an identity compute cluster configured to perform identity resolution for a plurality of objects, strip all personally identifiable information related to risk behavior for the objects, associate a link with each of the objects having data related to risk behavior, attach the link to corresponding data related to risk behavior for each of the objects, and output the data related to risk behavior for the objects; a pixel services compute cluster configured to receive online activity data, associate the online activity data with a particular online computing device, and output the online activity data associated with the particular online computing device to the identity compute cluster to facilitate identity resolution for the plurality of objects; a behavioral identity compute cluster configured to receive behavioral data, associate the behavioral data with a particular entity, and output the behavioral data associated with the particular entity to the identity compute cluster to facilitate identity resolution for the plurality of objects; a behavioral data platform configured to collect device behavioral activity associated with objects and to provide behavioral data to the behavioral identity compute cluster to facilitate identity resolution for the plurality of objects; a business-to-business (B2B) identity graph comprising a plurality of nodes each corresponding to a business entity, the identity compute cluster being configured to perform identity resolution for the plurality of objects by comparing data received at the identity compute cluster with the B2B identity graph; a partner platform comprising a plurality of employee electronic devices, each of the employee electronic devices comprising a web browser, the partner platform configured to provide data of a plurality of internet protocol (IP) addresses from the web browser to the pixel services compute cluster; a risk scoring compute cluster configured to receive the data related to risk behavior for the object from the identity compute cluster, calculate a cyber security score and report, receive feedback from an enterprise computing system, and recalculate the cyber security score and report using the feedback in real time; Equipped with The cyber security score is: calculating trait scores for a plurality of cyber risk traits including at least financial risk taking, social risk taking, recreational risk taking, conscientiousness, and decision-making; grouping the trait scores into behavioral buckets including at least risk propensity, decision making, and personality; calculating a behavioral bucket score by performing a weighted sum of the trait scores within each behavioral bucket; calculating a weighted sum of the behavioral bucket scores; The system is calculated by:

Images