Considerations for developing Big Data Security Analytics: A Practical Guide

50 %
50 %
Information about Considerations for developing Big Data Security Analytics: A Practical...
Technology

Published on March 2, 2014

Author: oracuk

Source: slideshare.net

Description

In this paper we outline an approach and highlight the
key considerations for applying Big Data to cyber security
analytics. Throughout we draw on the key lessons learned
from our own experience of implementing Big Data,
specifically Hadoop-based, cyber security analytics solutions.

CONSIDERATIONS FOR DEVELOPING BIG DATA SECURITY ANALYTICS: A PRACTICAL GUIDE

CONTENTS THE APPLICATION OF BIG DATA TO SECURITY ANALYTICS 3 A CHANGING THREAT LANDSCAPE 3 INCREASED MONITORING LEADS TO BIG DATA 3 BEHAVIORAL ANALYTICS FOR DETECTION 3 A BIG DATA PLATFORM FOR INVESTIGATION 4 DESIGNING AND PLANNING A SOLUTION 5 MAKE A BUSINESS CASE 5 CAPTURE REQUIREMENTS 5 CONSIDER RISKS IN THE MARKET 7 CHOOSING THE RIGHT TECHNOLOGY 8 CHARACTERISTICS FOR TECHNOLOGY SELECTION 8 IMPLEMENTATION DECISIONS 8 EARLY ADOPTER APPROACH 9 EXAMPLE OF A SUCCESSFUL DEPLOYMENT 10 OUR APPROACH 10 LESSONS LEARNED 10 SUMMARY 11 OUR BIG DATA SECURITY ANALYTICS 11 CYBERREVEAL 11 ADVANCED THREAT DETECTION 11 CYBER DATA CONSULTING SERVICES 11 2

BAE Systems Applied Intelligence INTRODUCTION “There are only two types of companies: those that have been hacked and those that will be. And even they are converging into one category: companies that have been hacked and will be hacked again.” Cyber security attacks are increasing in terms of their quantity, diversity and severity of impact. Simply securing the perimeter is no longer a realistic goal. Priorities for cyber security teams are shifting to more sophisticated monitoring and efficient investigation in order to identify attacks as quickly as possible and limit the damage. BAE Systems Applied Intelligence advocates a Big Data approach to cyber security analytics to address these priorities as the volume and variety of data from cyber security monitoring continues to grow. We were an early adopter of applying Big Data analytics tools and methods to cyber security analytics, building on our analytic and technical expertise and experience in related fields of fraud detection and intelligence analysis. ROBERT S MUELLER, III, FORMER DIRECTOR OF THE FBI INCREASED MONITORING LEADS TO BIG DATA Big Data is still risky business as the market continues to rapidly evolve; technologies are still emerging, necessary skillsets are scarce and many vendors are immature. There are significant benefits to be realized from applying Big Data to security analytics in terms of efficiency, scalability and cost effectiveness. However a well-planned, incremental and well mitigated approach is key to success. Cyber security analytics is rapidly becoming a Big Data application for one simple reason: large organizations are collecting, processing and analyzing more and more data in order to effectively address the new cyber threat landscape. The promise of Security Information & Event Management (SIEM) technologies was to deliver advanced analytics capabilities. The reality is that SIEM products weren’t designed for Big Data analytics and generally cannot meet the rapidly evolving needs that leading commercial organizations now demand. In this paper we outline an approach and highlight the key considerations for applying Big Data to cyber security analytics. Throughout we draw on the key lessons learned from our own experience of implementing Big Data, specifically Hadoop-based, cyber security analytics solutions. SIEM does provide a good foundation for security monitoring in providing a near real-time signature or rules-based detection capability to look for known threats. SIEM is also great for compliance and reporting. However, SIEM does not scale to detect the unknown threats across all the available data. Data often has to be pre-filtered before being loaded in to a SIEM. This effectively presupposes where the risk lies. SIEM cannot do the advanced security analytics that are required today. THE APPLICATION OF BIG DATA TO CYBER SECURITY ANALYTICS A CHANGING THREAT LANDSCAPE The cyber threat landscape has changed dramatically over the last 5 years. The new industrialization and internationalization of digital criminality combined with the limited legal responses available have enabled the dramatic growth and convergence of both simple and sophisticated attacks. It is likely the SIEM platforms and the current range of Big Data cyber security analytics platforms will move towards convergence over the next five years. However, this is new ground for both groups of vendors and for now separate products remain necessary to achieve the full potential benefits of each. It is now generally accepted, not only in the security profession but also in the Boardroom, that every organization will be attacked in one form or another on a regular basis. Some of those attacks will inevitably succeed. This is driving changes in the defensive stance of leading firms, where a higher emphasis is now being placed on identifying and limiting damage from successful attacks. Previously many had the now unrealistic goal of attempting to prevent all possible attacks. BEHAVIORAL ANALYTICS FOR DETECTION Behavioral analytics understand past human behavior, predict future behavior and identify anomalous behavior. Behavioral analytics have been used extensively in fraud detection and prevention because different individuals naturally display different behaviors from each other, as well as being different from a fraudster. Behavioral analytics takes advantage of this fact. Rather than just looking for specific indicators, behavioral analytics combines knowledge with monitoring to determine if behavior is expected and legitimate, or suspicious. Behavioral analytics is a Big Data challenge not only because of the volumes of data involved, but also because of the need to bring a wide variety of data sources and formats together to create a full picture. As a direct result, effective and efficient security operations have become a key cyber defense capability within many leading organizations. Innovative and leading commercial organizations are now building increased security monitoring and security analytics capabilities to sit alongside effective threat intelligence and critical incident management capabilities. Their goal is to predict, to limit and to manage the inevitable attacks they will face. 3

Cyber security analytics is increasingly adopting behavioral analytics, from the fraud detection field, in order to address the reality that traditional security solutions have proven ineffective against the incredible variety and volume of digital criminality, such as cyber espionage, cyber crime, hacktivism and the insider threat. This emerging cyber and fraud threat detection convergence means that the benefits realized from behavioral analytics in combating both will increasingly drive even greater operational efficiencies and investment decisions. A BIG DATA PLATFORM FOR INVESTIGATION Behavioral analytics are proving to be more robust, enduring and effective than traditional signature and rules based analytics. Figure 1 demonstrates the contrast between the two. In short, an organization using behavioral analytics will find anomalies that other point solutions and systems cannot. Big Data platforms can enable faster query times and a more seamless approach for security analysts retrieving and analyzing data across multiple sources and formats. A Big Data platform also provides increased storage, providing a deeper history to explore. The operational cost of the technology and people required to effectively detect, triage and investigate security incidents is too high. Limits on data collection, non-interoperable tooling and subsequent data mining means that once suspicious indicators have been identified it can take weeks for a cyber investigator to collect and analyze the data from across a large enterprise required to identify the appropriate response. Enduring: evasion requires fundamental changes to the threats modus operandi. Behavioral analytics Known bad: threats that have been seen before. Brittle: small changes to the threats modus operandi can evade detection. Risk-based: probable behavioral matches with a threats previous M.O. Binary: an event is either bad or not. General: can assess all classes of threats. Specific: only assesses particular instances of threats. Time-range: behaviors that extend over wider ranges of time can be analyzed. Point in time: a small window of time for event analysis. Figure 1: Contrasting behavioral analytics with traditional approaches to detection 4 Signature and rule-based Potentially bad: threats that look similar to expected threats.

BAE Systems Applied Intelligence •  How will your adoption of Big Data impact your existing security business functions? Bringing everything into a single Big Data platform significantly improves the operational efficiency of cyber analysts by reducing both the time and effort of understanding a single security event. It also improves the effectiveness of cyber investigators by providing more context and situational awareness for each investigation. •  Who in your organization will be using the big data platform? What new roles would you need to create (e.g. cyber data scientist, big data platform specialist)? Working with our clients it has been clear that in helping them develop their business case these questions have proven fundamental to deciding whether the investment is worth pursuing and if so, where to focus resources. DESIGNING AND PLANNING A SOLUTION CAPTURE REQUIREMENTS Implementing a Big Data solution for security analytics can be a significant challenge without the proper design and planning. From our experience key issues include: Requirements constitute a breakdown of the high level goals into more granular outcomes and specific characteristics of what your solution will deliver. When capturing requirements you should assess a number of factors: tools, people, process, data and knowledge, as defined in Figure 2. This will help to guide the process and ensure all the essential elements of the solution are accounted for. •  People with skillsets in Big Data engineering, data science and cyber security are scarce; •  The technologies are emerging and complex;. •  There is no shortage of vendors promising to solve all your security analytic challenges; TOOLS •  cquisition of appropriate hardware and A software components C •  onfiguration and maintenance of technology components There needs to be a compelling business driven case that •  clearly defines your particular goals and business benefits that your Board will prioritize. Getting your solution right needs effective requirements capture, strong planning and a business-driven strategy. PEOPLE E •  nsuring that the staff involved is appropriately skilled E •  ngaging and training the necessary stakeholders MAKING THE BUSINESS CASE First, clarify the key goals and benefits that you want to realize for your organization by implementing a Big Data cyber security analytics solution. These will be driven by external factors, primarily the threats faced by your organization, as well as other internal priorities and the current security posture. Your high level goals should be quantifiable and where possible specified alongside target metrics. In our experience some common themes for high level goals are: PROCESS E •  ssential processes required for effective and sustained delivery of a security analytics function •  ecessary operational controls and metrics N DATA •  aw data sources from across the business that R will feed the security analytics platform •  ata that provides necessary context to interpret D and prioritize analytic results •  Detecting sophisticated attacks not visible in the SIEM •  Increasing the efficiency and speed of security incident investigations KNOWLEDGE •  he desired outcomes of the security T analytics capability •  Cost effectively scaling security analytics to the long-term needs of the organization Next, think about some high level questions and determine whether you have a strong business case to pursue implementation: Figure 2: Themes for capturing requirements •  How well do your key goals or threat scenarios map to available data sources? •  you really have a “big data” problem? What are Do the likely costs and benefits to implementation, verses continuing to use your existing tools? •  What functions do you want to move onto a big data platform (triage, investigation, research, metrics, management decisions)? 5

Requirement themes can be further broken down into elements that are either outcomes or activities. Some common elements are shown by theme in Figure 3. One way of formulating requirements is to consider your current security posture in terms of each element against the target security posture you wish to achieve by implementing a Big Data cyber security analytics solution. Data quality management Platform change management Stakeholder direction Analytic development PROCESS Legal oversight Access & security Alert management Sensors Support Visualization Research & development Onboarding data sources TOOLS Log management Stewardship Performance metrics & reporting Hardware investment SIEM Storage Senior stakeholder trust, understanding and enthusiasm Data Analysis skills Deployment & management Data source access Analytic framework Big Data engineering skills PEOPLE Training Cyber skills Incident case history Vulnerability managemtent data Internal enrichment (e.g. HR data) Threat intelligence Security KPIs Events / incidents Security operations data (e.g. web proxies, email logs) Contextual trends DATA KNOWLEDGE Behaviors Threat model OSINT reports Security performance Organization assets identification Insiders Security posture Figure3: Common elements of requirements for each theme 6

BAE Systems Applied Intelligence CONSIDER RISKS IN THE MARKET The marketplace for Big Data and particularly Big Data for security analytics is emerging and constantly changing. This introduces particular risks that should be taken into account in your planning stage. Table 1 summarizes the key risks in the market today. There will also be additional risks that are specific to your organization that need to be accounted for and appropriately mitigated. Issue Risk Mitigation Emerging technologies Software components could change and not provide backward compatibility to existing applications, leading to rework. Adoption of components with strong open source community backing (e.g. Apache top-level projects) or working with partners with expertise in specific technologies. Commercial vendors cease to provide support to the software components. Adoption of a solution based on widely used open source components or established vendor backing. The solution becomes dependent on a proprietary software component that restricts you from changing your commercial vendor, leading to increased support costs and reduced agility. Avoid critical platform dependencies on proprietary Big Data technologies. Also, require vendors to ensure their infrastructure stack is open and can co-exist with other operational use cases. A Big Data software platform could include non-Big Data components that limit scalability, leading to reduced value or increased costs. Obtain confirmation and demonstrable capability from vendors that they adopt Big Data technologies for the core operational use cases. The solution is more expensive than planned leading to budget overrun and reduced cost effectiveness Avoid dependencies on vendors for key support services where those services are not included in the product package. Technologies are still developing and it is possible that there will be significant changes to the available software components in the future. Commercially immature supplier market Many companies providing the commercial options are start-ups and are not yet profitable. It is likely that some suppliers will fail or be acquired by larger companies. Proprietary components Some vendors extend open source tools with proprietary extensions in order to provide more value to their clients. Others offer specific applications for information security that often require a proprietary Big Data infrastructure stack. Overuse of the term ‘Big Data’ Some vendors are using the term Big Data to describe solutions but this can obscure a mixed Big Data / legacy platform, which is limited by the legacy components. Hidden costs When buying some solutions it may not be clear what all the additional costs involved are. For example professional services required for configuration or training. Table 1: Risks in the market for Big Data security analytics  7

CHOOSING THE RIGHT TECHNOLOGY IMPLEMENTATION DECISIONS In addition to considering the risks in the market and the key characteristics, there are three principal implementation decisions for technology that you will need to consider when implementing a Big Data cyber security analytics solution today: Given the emerging Big Data market, new approaches and tools will be developed regularly and new vendors are continually appearing. Before acquiring new technology to implement a Big Data cyber security analytics capability, you should complete a thorough analysis of the options available and measure them objectively against your particular requirements. Choice of technology: Hadoop vs. not Hadoop Apache Hadoop has been the rising star of the Big Data technology market in the past few years. It has enabled organizations to explore their data at a scale previously prohibited through hardware and software costs. However, Hadoop is not a Big Data panacea and there are alternatives such as Google’ BigQuery service or Netezza processing engines that are often more mature. CHARACTERISTICS FOR TECHNOLOGY SELECTION Technology selection will be driven by your requirements, but there are some key characteristics that we recommend should be sought in order to mitigate and manage the risks within the current market. These are summarized in Table 2. Open architecture Choose open platforms over proprietary application stacks or suites. Preserve the option to change vendors as much as is practical in order to avoid vendor lock-in. Modular components The main considerations for this decision are the availability of skillsets for deployment and management, the required scalability of the platform for storage and processing, and the extent to which the architecture is open. Given the rapid evolution of the Big Data market these factors should be projected forward. For example given its growing popularity the availability of Hadoop skills is likely to increase significantly over the next few years. Select components that are decoupled from the overall platform to allow best of breed components to be intermingled as requirements and best-practices become clearer. Scalable Extensible Secure Hardware acquisition and management: in-house vs. outsource One of your key decisions, particularly if you adopt Hadoop, is the hardware environment. Consideration must be given to both the initial deployment and its on-going management. Prioritize your ability to linearly scale out the platform as it is likely that the breadth and complexity of the data being analyzed will increase and that the demands on a successful Big Data cyber security analytics function will increase over time. One option is to acquire commodity hardware and have your engineers deploy the Hadoop distribution of choice onto it. Alternatively you can outsource the deployment and management of the Hadoop distribution. The can be achieved in a variety of ways including; outsource Hadoop deployment and management on commodity hardware to a Platform as a Service (PaaS) provider, or to acquire a Big Data appliance, which offers an out-of-the-box hardware and software solution with a Hadoop distribution already installed and configured. Choose a platform and components that can have functionality added to them as your requirements for Big Data cyber security analytics mature and the teams’ understanding of the subject matter develops. Availability of Big Data skillsets and desired levels of vendor support will be driving factors in this decision. You also need to compare the cost effectiveness of the options, to include the hardware, software and human resource costs involved. Be mindful of both the increasing value of the Big Data platform to a sophisticated attacker and the likely sensitivity of the increasing range of datasets it will store. While security requirements at the outset are likely to be low, build a platform with the ability to enable robust security as required. Security Analytics: Off the shelf security analytics Vs. Build your own The majority of vendors in the Big Data solutions market are offering generic solutions that allow you to build analytics from scratch. However, as the value of Big Data for cyber security analytics becomes more widely recognized, there are a growing number of vendors offering Big Data solutions specifically for cyber security analytics. Such solutions can offer a significant head start for you in the development of effective Big Data cyber security analytics. Table 2: Key characteristics for technology selection  8

BAE Systems Applied Intelligence The extent to which you decide to utilize ‘pre-canned’ Big Data cyber security analytics should be weighed against the limitations that some solutions can impose on your Big Data platform. The decision will come down to what your longer term goals are for cyber security analytics. For example, if you eventually plan on having security analysts writing their own behavioral analytics with Hadoop MapReduce you will want to avoid solutions that lock you in to a proprietary Big Data platform and prevent use of that platform in any other capacity. “Hadoop’s momentum is unstoppable as its open source roots grow wildly into enterprises’” MIKE GUALTIERI, FORRESTER An important consideration for this decision is to closely analyze what Big Data features a security analytics solution is actually providing and whether those solutions fully harness the capabilities that Big Data technology enables. For example a number of the Security Analytics vendors that advertise Hadoop-based capabilities only use Hadoop for storage and still rely on their existing platforms for the processing capability. EARLY ADOPTER APPROACH The application of Big Data to security analytics is still in the early adopter phase. Much will change in both the Big Data and the security analytics markets in the near future, so we advocate an approach to implementation guided by the principles described in Figure 4. EXPERIMENTAL INCREMENTAL DEVELOPMENT •  Develop the capability with the assumption that some of the opportunities envisioned will fail to deliver •  Build the platform and the analytics one piece at a time and grow the capability incrementally rather than deliver a ‘big-bang’ project •  Celebrate failures as opportunities to learn about the overall approach BUILD EXISTING SKILLS MEASURED •  Build the capability to enable staff to re-use existing skills as much as practical •  Set clear metrics for planned operational benefits •  Ensure capability developed allows for the measurement of those metrics •  Train existing staff, rather than try to recruit expert staff from the market Figure 4: Guiding principles for implementation approach 9

EXAMPLE OF A SUCCESSFUL DEPLOYMENT LESSONS LEARNED Computer science PhDs don’t scale very easily or cost effectively – account for multiple types of user We began with a team of 8 researchers looking at the emerging cyber security market and how we could apply Big Data to the problem. At this stage our technology requirements were shaped by the need for low risk/low cost ideas for setup and scalability. Hadoop provided a cost effective option to get started as it was free to download (plus some low cost servers) and it also met our critical requirement for enabling analysis at scale. Some of our clients and other areas of our business were already successfully using Hadoop for different business use-cases – in fraud detection for example. Hadoop Map-Reduce also provided a suitable analytic framework to pursue behavioral analytics, which we realized would be necessary in order to detect the more sophisticated attacks that were becoming increasingly prevalent at that time. The small pilot team had the necessary data engineering and data science skillsets to deploy, manage and write analytics with Hadoop. We needed to do more to define the separate skill sets required across areas of the platform and provide appropriate interfaces for each type of user in order to scale. This led to the development of our investigator tool to provide context, visualization and decision support to security operation analysts. This investment has improved operational efficiency and enabled us to scale the team with non-developer analysts. Map out the end-state operational context at the outset This gave us a base technology platform for experimentation but we still had minimal operational capability and limited ability to consistently deliver good security outcomes. The tipping point in operationalizing our capability came when we were asked to investigate a sophisticated targeted attack against one of our clients. As a result we needed to consider the wider ecosystem of people, processes and services around the core big data platform. Our approach was very technology focused at inception. Mapping out the end-state operational context at the outset alongside the design of the technology would have prevented us from investment in activities that did not ultimately support the end goal. Big data as a technology is not a solution in itself; it is an enabler to more effective and efficient security operations when planned and executed in the right context. Measuring progress and performance is essential Unless you have a clear understanding of your current security posture it is very difficult to quantify any benefit to the application of new technology and methods. This is important for justifying the investment made. At a more granular level benchmarking performance enables you to identify bottlenecks and understand the impact of different configuration options to get the most out of the platform. Build in security to the Big Data platform from the start Given the nature of the data involved, a Big Data security platform can itself become an asset requiring cyber security protection. It is much easier to build this security in from the start rather than add it in later. For Hadoop security consider the environment in which you want to operate the platform and build the surrounding controls accordingly. The BAE Systems Applied Intelligence CyberReveal product has been created following this approach. What started out as an in-house solution, experimenting with Big Data technologies to address our own cyber security threats and risks, has evolved into a Big Data cyber security analytics capability that can be applied across many industries. OUR APPROACH From there we grew a service we could offer customers to provide security monitoring of their network to detect sophisticated attacks, which were largely going undetected, based on the more traditional Anti-Virus, Intrusion Detection Systems and SIEM platform based approaches prevalent in the market at the time. In more recent years awareness of the cyber threat has grown and many organizations are now maturing their own internal security operations. We realized that the technology and experience we have in our security monitoring service would be valuable to others looking to do the same. We packaged the core components that underpin our security monitoring service into the initial CyberReveal product, which continues to develop as a Big Data solution for cyber security incident detection and investigation. Table 3: Lessons Learned 10

BAE Systems Applied Intelligence SUMMARY BIG DATA CYBER SECURITY ANALYTICS IN BAE SYSTEMS APPLIED INTELLIGENCE As a result of the rapidly changing and expanding cyber threat landscape many organizations have increased their security monitoring capabilities both in terms of volume and variety of data. As such cyber security analysis is now becoming a Big Data challenge for both the detection and investigation of incidents. BAE Systems Applied Intelligence advocates maximizing the utility of Big Data tools and techniques for storage, processing and analysis. In particular we advocate using Big Data for behavioral analytics that provide a more robust, enduring and effective approach to cyber security analytics than more traditional methods. BAE Systems Applied Intelligence offers a variety of products and services designed to accelerate the applications of Big Data to security analytics. CYBERREVEAL® CyberReveal is the multi-threat monitoring, analytics, investigation and response product. It enables security analysts to identify and manage cyber threats quickly and efficiently, by providing big data correlation, security analytics, contextual information linking and threat intelligence, all in one powerful product. For organizations considering investment in a Big Data cyber security analytics solution, effective planning and risk mitigation is the key to success. The business case behind any investment should be driven by specific business driven goals and measurable benefits. A full requirements capture exercise should consider all factors that will be part of the solution including the technology, people, process, data and knowledge. Mitigation strategies against the risks of the evolving Big Data market should ensure the solution is adaptive and resilient to the inevitable changes that we will see over the next 5 years. CyberReveal is a true Big Data cyber security analytics and investigation platform, bringing together BAE Systems Applied Intelligence’s heritage in network intelligence, big data analytics and cyber threat research into a unique enterprisescalable product. CyberReveal comprises of three core components The choice of technology should be strongly driven by your particular requirements but the characteristics of scalable, extensible, open , modular and secure must also be factored into your choice. There is an ever growing selection of products and services available in the Big Data market and specifically the cyber security Big Data market. Organizations should pay particular attention to the skillsets required for different options, the cost effectiveness for the different ways of standing up a Big Data platform as well as the true extent to which solutions take advantage of the advances that Big Data technology allows. •  Platform: Massively scalable technology platform that correlates data acquired from across the IT infrastructure •  Analytics: Behavior-based threat detection using unique attack models and our latest research •  Investigator: Powerful threat intelligence management and investigation toolset providing visualizations, rich contextualization and correlation of threats, indicators, events and alerts. Designed by analysts, for analysts. ADVANCED THREAT DETECTION BAE Systems Applied Intelligence was an early adopter of Hadoop. We followed an experimental and incremental approach in applying Hadoop and related Big Data technologies to cyber security analytics. Over the last five years we have grown this experiment into a range of award winning products and services that form our Big Data cyber security solutions portfolio for world-class security incident detection and investigation. Advanced Threat Detection is a managed service that monitors your network for sophisticated attacks hiding in legitimate activity to breach your perimeter defenses. Our CyberReveal platform analyses the behavior of devices on your network and their connections with the Internet to pick out attacks from within legitimate network traffic. Skilled security analysts investigate suspicious activity and raise security incidents when you need to take action. Our Threat Intelligence function monitors key attack groups, ensuring that the latest techniques can be detected quickly and effectively. Advanced Threat Detection helps you to stop sophisticated attacks with the potential for serious impact to your business before the damage is done CYBER DATA CONSULTING SERVICES Our strategic cyber consultants and data analytics experts combine to help organizations define and implement an appropriate strategy to guide the adoption and the application of Big Data analytics techniques to cyber security. 11

ABOUT US We deliver solutions which help our clients to protect and enhance their critical assets in the intelligence age. Our intelligent protection solutions combine large-scale data exploitation, ‘intelligence-grade’ security and complex services and solutions integration. We operate in four key domains of expertise: Cyber Security, financial crime, communications intelligence, and digital transformation. Leading enterprises and government departments use our solutions to protect and enhance their physical infrastructure, missioncritical systems, valuable intellectual property, corporate information, reputation and customer relationships, competitive advantage and financial success. We are part of BAE Systems, a global defense, aerospace and security company with approximately 90,000 employees. BAE Systems delivers a full range of products and services for air, land and naval forces, as well as advanced electronics, security, information technology solutions and customer support services. For more information contact: BAE Systems Applied Intelligence 265 Franklin Street Boston MA 02110 USA Copyright © BAE Systems plc 2014. All rights reserved. BAE SYSTEMS, the BAE SYSTEMS Logo and the product names referenced herein are trademarks of BAE Systems plc. BAE Systems Applied Intelligence Limited registered in England & Wales (No.1337451) with its registered office at Surrey Research Park, Guildford, England, GU2 7YP . No part of this document may be copied, reproduced, adapted or redistributed in any form or by any means without the express prior written consent of BAE Systems Applied Intelligence. CYNCIWPAM_BEAU0214_bigdata_V1 T: +1 (617) 737 4170 E: marketingai@baesystems.com W: www.baesystems.com/ai

Add a comment

Related presentations

Related pages

Considerations for developing Big Data Security Analytics ...

... started in Big Data Security Analytics. ... A practical guide for getting started in Big Data ... Considerations for developing Big Data ...
Read more

Australian Public Service - Better Practice Guide for Big Data

Better Practice Guide for Big Data ... and privacy are key considerations in all big data ... and security to data analytics are covered in ...
Read more

Data Analytics—A Practical Approach - Information ...

Data Analytics—A Practical Approach ... Web Application Security: Business and Risk Considerations. ... A Practical Guide to the Payment Card ...
Read more

Part 1 Whitepaper - Why Use Big Data for Cyber Security? A ...

A Practical Guide Big Data Security Analytics. by BAE Systems Applied Intelligence. Mar 03, 2014. ... The CISOs Guide to Spear Phishing Defense
Read more

Australian Public Service - Department of Finance

Big Data and Big Data Analytics Better Practice Guide 2 ... Australian Public Service Big Data ... security and privacy are key considerations in all ...
Read more

5 Recommendations for Developing a Big Data Analytics Strategy

5 Recommendations for Developing a Big Data ... big data analytics, ... roadmap to guide the organization through practical approaches ...
Read more

Big data tutorial: Everything you need to know

Big data tutorial: Everything you need to know. ... Big data analytics can use real ... The following links present some common big data security and ...
Read more

Developing big data solutions on Microsoft Azure HDInsight

Developing big data ... and Analytics product range. This guide ... In terms of the “whys,” the guide explains the concepts of big data ...
Read more

Introduction to Big Data: Infrastructure and Networking ...

... Infrastructure and Networking Considerations ... • financial services providers are adopting big data analytics ... Introduction to Big ...
Read more

Understanding Microsoft big data solutions

Developing big data solutions on Microsoft Azure HDInsight Understanding Microsoft big data solutions
Read more