1. Prelert Blog

    1. John O’Donnell Joins Prelert as CFO to Support Company’s Accelerated Growth Strategy

      Explore businesswire.com (Feb 10 2015)

      John O’Donnell has joined Prelert, the leading provider of machine learning anomaly detection, as Chief Financial Officer. In this role, he will manage all financial, legal, human resources and administrative operations, working directly with Prelert’s senior management team to drive growth and success in each area. With more than 20 years of industry experience, O’Donnell most recently served as CFO of Aveksa, a leading provider of business-driven identity and access management software. While there, he built a global finance and administration organization to support the company’s dynamic growth, leading to its eventual acquisition by EMC Corporation. 

      (Read Full Article)

      Comment Mentions:   CA Technologies   Mark Jaffe

    2. Today's IT Challenges Require Advanced Analytics

      Explore Anomaly Detection Analytics (Feb 4 2015)

      Today's IT Challenges Require Advanced Analytics

      In both IT security and operations, a common complaint is the overwhelming "noise" of largely false positive alerts generated by problematic detection systems. In both cases as well, the lack of information contained in these alerts forces a diagnostic or investigative approach requiring humans to manually mine through huge volumes of data as they search for unusual behavior patterns that might not even be detectable by the human brain.

      (Read Full Article)

      Comment Mentions:   Analytics

    3. Data Breach Notification: You Need to “Know” Before You Can “Notify”

      Explore Anomaly Detection Analytics (Jan 26 2015)

      Data Breach Notification: You Need to “Know” Before You Can “Notify”

      Data breach notification is not simply a matter of “fessing up” when your customer’s data has been compromised. The devil is in the details. Before an organization can “notify” about a data breach, it first has to realize that something happened, figure out what happened, when it happened, what data was accessed, and which individuals were affected. In other words, the organization needs to “know” before it can “notify.”

      (Read Full Article)

      Comment Mentions:   IT Security   Analytics   Breach

    4. Temporal vs. Population Anomaly Detection

      Explore Anomaly Detection Analytics (Jan 14 2015)

      Temporal vs. Population Anomaly Detection

      Some anomalous behaviors are temporal in nature (with respect to time) while others are population based (all others). But, what are the differences between these two types of anomalies and under what circumstances would you use one kind over the other? This blog discusses the details behind the analyses, their merits, and best practices based upon common rules of thumb.

      (Read Full Article)

      Comment Mentions:   IT Security   Analytics

    5. Security Analytics Use Case: Finding Document Thieves

      Explore Anomaly Detection Analytics (Jan 6 2015)

      Security Analytics Use Case: Finding Document Thieves

      From time to time, document thieves may gain access to [institutional] accounts (probably through phishing attacks) and use them to access licensed material (journals, for instance) that only [authorized] users have access to.  These documents are often resold in a sort of intellectual property black market. The goal is to proactively detect these sorts of situations and quickly suspend the compromised accounts, rather than waiting to notice that the content is stolen...

      (Read Full Article)

      Comment Mentions:   Analytics

    6. Anomalies as Unexpected or Rare Events by Time of Day

      Explore Anomaly Detection Analytics (Dec 31 2014)

      Anomalies as Unexpected or Rare Events by Time of Day

      This discussion deals with the uniqueness of an event occurring at a specific time, such as a user logging in at an unexpected time of day for that user...

      (Read Full Article)

      Comment Mentions:   Prelert

    7. The Secrets to Successful Data Mining

      Explore Anomaly Detection Analytics (Dec 16 2014)

      The Secrets to Successful Data Mining

      Today's IT environments are so complex that IT and DevOps teams cannot reasonably set thresholds and alerts across all meaningful metrics. Even the much-touted best practice of employing standard deviations fails when the actual distribution of values is not Gaussian. Trying to manually define anomalies in increasingly complex systems can result in a deluge of false alerts that waste your IT team's valuable time. In fact, in a random sampling of Splunk users, almost half did not bother setting thresholds for fear of creating additional "alert noise." Scary, huh?

      (Read Full Article)

      Comment Mentions:   Enterprise Management Associates

    8. Why IT Security Teams Need Machine Learning

      Explore Anomaly Detection Analytics (Dec 12 2014)

      Why IT Security Teams Need Machine Learning

      It turns out that finding anomalies in huge volumes of data is exactly what Big Data analytics approaches, such as unsupervised machine learning, are good at...

      (Read Full Article)

      Comment

    9. Security Analytics - Anomaly Detection for IT Security

      Explore Anomaly Detection Analytics (Dec 5 2014)

      Security Analytics - Anomaly Detection for IT Security

      In this short (1:25) video, IT Security professionals protect from advanced threats with security analytics. Machine learning anomaly detection finds the fingerprints of criminial activity in real-time so to detect problems early and act fast...

      (Read Full Article)

      Comment Mentions:   IT Security   Analytics

    10. Data Mining: Don't Settle for Monitoring 1% of Your IT Operations Data

      Explore Anomaly Detection Analytics (Dec 4 2014)

      Data Mining: Don't Settle for Monitoring 1% of Your IT Operations Data

      Do you have the whole automation vs. data mining thing backwards? Traditional IT monitoring approaches automatically analyze less than 1% of the data available looking for 'known bad' behaviors. When a problem is found, an alert is raised that tells us what happened. Troubleshooting teams then have to manually ‘mine’ the other 99% of the data to find out why there was an alarm in the first place. No wonder recent surveys on the state of IT operations verify that two of the biggest concerns are "time spent troubleshooting" and "problems reported by users before IT knows about them."

      (Read Full Article)

      Comment Mentions:   Troubleshooting

    11. Ensure Compliance With IT Operations Analytics

      Explore Anomaly Detection Analytics (Dec 3 2014)

      Ensure Compliance With IT Operations Analytics

      With ITOA (IT Operations Analytics), companies no longer have to remain well-read on each potential flaw or hack that has been concocted and can set up the technology to look for users that are operating outside the definition of normal. The automated nature of ITOA technology frees a company's IT team from having to set thresholds, develop signatures, or just manually search for abnormal behaviors. The ability of ITOA technology to adapt with speed and accuracy minimizes false positives and provides an organization with the resource it needs to weed out any rogue marketers before they get a chance ...

      (Read Full Article)

      Comment Mentions:   Analytics

    12. Implementing StatsReduce in Anomaly Detective

      Explore Anomaly Detection Analytics (Nov 20 2014)

      Implementing StatsReduce in Anomaly Detective

      One of the major additions to version 3.3 of Prelert Anomaly Detective ® for Splunk was a feature called StatsReduce. This feature enables Anomaly Detective to take advantage of Splunk’s distributed processing to analyse immense volumes of data quickly enough to deliver real-time insights. The addition of StatsReduce mode to our Anomaly Detective for Splunk makes it the sole native Splunk app that can deliver real-time analytics for data big enough to require a distributed Splunk installation to store it.

      (Read Full Article)

      Comment

    13. Anomaly Detection on Large Data Sets via Aggregation

      Explore Anomaly Detection Analytics (Nov 18 2014)

      Anomaly Detection on Large Data Sets via Aggregation

      When dealing with very large data sets, there are various practical obstacles, which aren't present at smaller scale, to getting conventional anomaly detection algorithms to work. A key one is the concept of data inertia. This is simply that it is impractical or even impossible to transport the entire data set to a single process. Often, in this context, we have to process a distributed collection of data streams, and we simply don’t have the bandwidth to copy all these data to one process. Therefore, we would like to be able to perform anomaly detection at the level ...

      (Read Full Article)

      Comment

    14. IoT Won’t Work Without Artificial Intelligence

      Explore Anomaly Detection Analytics (Nov 14 2014)

      IoT Won’t Work Without Artificial Intelligence

      As the Internet of Things (IoT) continues its run as one of the most popular technology buzzwords of the year, the discussion has turned from what it is, to how to drive value from it, to the tactical: how to make it work. IoT will produce a treasure trove of big data. This data will hold extremely valuable insight into what’s working well or what’s not – pointing out conflicts that arise and providing high-value insight into new business risks and opportunities as correlations and associations are made. It sounds great. However, the big problem will be finding ways ...

      (Read Full Article)

      Comment Mentions:   Artificial Intelligence

    15. How to Find Anomalies in Splunk's Internal Performance

      Explore Anomaly Detection Analytics (Nov 10 2014)

      How to Find Anomalies in Splunk's Internal Performance

      Splunk does a great job of keeping track of its own internal logs and performance information, and there’s even a very useful and concise app called “S.o.S” (Splunk on Splunk), which tracks and reports on a variety of items culled from Splunk’s “_internal” index and a variety of source logs such as the splunkd.log file. But, just like any visual report or dashboard, there are some fundamental limitations to making this data proactive. Anomaly Detective makes it ridiculously easily to bring machine learning-based anomaly detection to your Splunk on Splunk data!

      (Read Full Article)

      Comment

    16. Prelert Closes $7.5M Investment from Intel Capital and Existing Investors

      Explore Yahoo! Finance (Nov 4 2014)

      Prelert , the anomaly detection company, today announced it has raised a $7.5 million round of venture capital financing from Intel Capital and existing investors, Fairhaven Capital and Sierra Ventures . This investment will enable Prelert to further expand its field sales and engineering organizations to leverage the growing interest in Anomaly Detective® from enterprises, cloud service providers and IT management providers...

      (Read Full Article)

      Comment Mentions:   Intel   CA Technologies   APM

    17. C++11 mutex implementations

      Explore Anomaly Detection Analytics (Nov 3 2014)

      C++11 mutex implementations

      C++11 brought concurrency to standard C++ for the first time. Prior to this the only choice for writing multi-threaded C++ programs was to use a separate C++ library, such as Boost Thread or Intel Thread Building Blocks , or roll your own wrappers around the low-level operating system facilities, such as POSIX threads or Windows threads . Last year I looked into the performance of different types of locks on different platforms. The variation in performance is surprisingly wide. Prelert’s codebase pre-dates C++11, so we have our own wrappers around the low-level operating system facilities. Here are the ones ...

      (Read Full Article)

      Comment Mentions:   Intel

    18. Machine Data is Different (and Why It Matters)

      Explore Anomaly Detection Analytics (Oct 13 2014)

      Machine Data is Different (and Why It Matters)

      Why is machine data different? To answer this question, let’s start by considering different perspectives on what constitutes unstructured data. In the case of a pre-defined set of allowed classifications, the standard approach for benchmarking a machine-learnt classification against a human-generated correct result is to use a confusion matrix . Each of the allowed classifications corresponds to a row and a column in the matrix, and the cells in the matrix record the number of input messages with corresponding human-generated classification and machine-determined classification. The perfect outcome is for all cells of the matrix to contain zeroes except those on ...

      (Read Full Article)

      Comment Mentions:   Prelert

  1. Recent Articles for IT Ops & APM

    1. Gartner Q&A: Cameron Haight Talks About DevOps

      Explore APMdigest (Feb 26 2015)

      Jonah Kowall has taken a VP position at AppDynamics, and Cameron Haight, has replaced Jonah as Gartner's leading APM specialist. Here, Cameron Haight discusses his background. In addition, Cameron previously published this open letter to APM vendors: http://performancecriticalapps.prelert.com/articles/503434/open-letter-from-gartner-to-apm-vendors/

      (Read Full Article)

      Comment Mentions:   IBM   Google   Application Performance Management

    2. Open Letter From Gartner to APM Vendors

      Explore Gartner Blog Network (Feb 10 2015)

      Dear APM vendor: As I step back into covering the application performance monitoring market, I’d like to try to optimize the time during our discussions (particularly briefings). So with that in mind, I offer the following suggestions for your consideration: 1) Please don’t just iterate through (multiple pages of) the litany of problems that exist within the industry (and that you intend to solve). After many years within IT, I’d be a pretty poor analyst if I didn’t already know at least most of them...

      (Read Full Article)

      Comment Mentions:   Application Performance Management   Amazon   APM

    3. Log Data Outranks Traditional Data Sources for Network Operations Management

      Explore APMdigest (Feb 6 2015)

      EMA has been tracking the role that network log data plays in network management disciplines for years. What is most striking is that log data now outranks traditional network management data sources such as SNMP, NetFlow, and packet analysis as most heavily used and valued for multiple use cases.

      (Read Full Article)

      Comment Mentions:   BSM   CA Technologies   Application Performance Management

    4. Advanced Persistent Threats: Minimizing losses with early detection

      Explore Help Net Security (Jan 28 2015)

      Attackers try hard to mask their activities – but try as they might, in order to accomplish their goals, their behaviors are likely to be anomalous at some point in time. Quickly detecting these anomalies as they develop could make the difference between losing tens of millions of customer records and losing a few hundred – or none at all.

      (Read Full Article)

      Comment Mentions:   Cisco   Analytics

  2. Recent Articles for Security Analytics

    1. Are You Overlooking 5 Critical IT Security Measures?

      Explore smartdatacollective.com (Feb 26 2015)

      Let me ask you something: How well equipped is your company to deal with and respond to a potential data breach? On a scale of 1-10. Do you know? Not sure? Experian put out an interesting report regarding data breach preparedness. They found that 23% of respondents believed that their organization doesn’t understand what needs to be done following a material data breach to prevent loss of customer and client trust.

      (Read Full Article)

      Comment Mentions:   BYOD   IT Security   Breach

    2. 3 reasons SSL encryption gives a false sense of security

      Explore Networks Asia (Feb 25 2015)

      Last year’s high-profile Secure Sockets Layer (SSL) vulnerabilities, such as Heartbleed and Padding Oracle On Downgraded Legacy Encryption (Poodle), have exposed weaknesses in the technology...

      (Read Full Article)

      Comment Mentions:   Application Performance Management   Gartner

    3. 3 dominant trends that will drive cloud security in the coming years

      Explore Information Age (Feb 11 2015)

      2014 saw significant change in the IT security industry – the cloud became real as large enterprises furthered adoption. Changes in infrastructure environments require changes in how organisations protect against threats. CIOs are now moving their focus from preventing a breach to accepting it and the requirement for fast detection, analytics and identifying vulnerabilities before they are exploited.Here are the dominant trends that are shaping cloud security for the next few years.

      (Read Full Article)

      Comment Mentions:   Google   Microsoft   Amazon

    4. The security implications of IoT: A roundtable discussion with four experts

      Explore Network World (Feb 10 2015)

      IoT is the Wild West right now. We don’t know what it’s going to look like, where it’s going. We’re right at the cusp and, while there’s a lot of opportunity, there is an intrinsic vulnerability because too often security is bolted on after the fact.

      (Read Full Article)

      Comment Mentions:   Cisco   Analytics

  3. Recent Articles for Big Data in IT

    1. What are the top data analytics platforms of 2015?

      Explore Agenda I The World Economic Forum (Feb 3 2015)

      Here is a rundown, in no particular order, of ten of the best and most widely used of these services. Like any commercial product in a competitive market, each has its advantages and disadvantages, and you need to make sure you are picking the right tool for the job...

      (Read Full Article)

      Comment Mentions:   Google   Microsoft   Amazon

    2. Big Data: Careful! When Correlations Go Crazy

      Explore smartdatacollective.com (Feb 3 2015)

      In the world of big data, strange truths about the world begin to emerge. Orange cars are the most reliable used cars to buy. Prepaid phone card sales can predict unrest in Africa. And women with larger breasts spend more money online...

      (Read Full Article)

      Comment Mentions:   Amazon   Big Data   Analytics

    3. Tackling the hard problems in IT security analytics

      Explore metaforsoftware.com (Jan 28 2015)

      The fast evolving nature of attack techniques means that patterns are constantly changing and new attack vectors are constantly emerging. Writing rules, signatures, and static models into defenses simply isn’t enough. The challenge is finding new associations and uncovering patterns to identify clues about attacks in real time, and without any human intervention. In many cases, whether the underlying relationship is causal or correlative is irrelevant. As Jeff Hopper of Bell Labs said:

      “Data do not give up their secrets easily. They must be tortured to confess.”

      (Read Full Article)

      Comment Mentions:   IT Security   Analytics

    4. Anomaly Detection: Finding Black Swans in Big Data

      Explore Network World (Jan 28 2015)

      Say hackers have infiltrated your network and FTPing customer account data to an external site. Noticing that one server amongst several hundred in your organization that doesn’t usually establish FTP sessions is doing so once every ten minutes would be a needle in a haystack situation given the sheer volume of all other transactions. To find this you'd need to have characterized your network traffic and have a tool capable of detecting relatively anomalous behavior in huge amounts of network data. This is definitively a Big Data problem and, moreover, it’s a realtime Big Data problem because ...

      (Read Full Article)

      Comment Mentions:   Big Data

  4. Recent Articles for Machine Learning Analytics

    1. IoT Won’t Work Without Artificial Intelligence

      Explore Wired.com (Nov 13 2014)

      In an IoT situation, machine learning can help companies take the billions of data points they have and boil them down to what’s really meaningful. The general premise is the same as in the retail applications – review and analyze the data you’ve collected to find patterns or similarities that can be learned from, so that better decisions can be made.

      (Read Full Article)

      Comment Mentions:   Artificial Intelligence   Mark Jaffe

    2. Making Sense of IoT Data With Machine Learning Technologies - Forbes

      Explore forbes.com (Sep 4 2014)

      As companies embark on the long journey of harvesting large amounts of data from connected devices and sensors, the valuable insights hidden in the data are driving up costs and not adding to the bottom line. How can these companies get these insights to market faster while reducing the risk of project failure? One way is to leverage the expertise of companies whose core competency is machine learning. One interesting use case comes from Prelert, a self-described anomaly detection company...

      (Read Full Article)

      Comment Mentions:   Prelert

    3. Sophie Chang Named VP of Engineering at Preler

      Explore businesswire.com (Aug 12 2014)

      Prelert , the anomaly detection company, today announced that it has hired Sophie Chang as Vice President of Engineering to lead its U.K.-based engineering team. In this role, Chang will be responsible for product development and managing all aspects of the team’s activities, helping to enhance Prelert’s machine learning-based anomaly detection engine. Chang brings more than ten years of senior executive experience to her new role, most notably through her time as VP Software at 1E, a fast-growing and successful B2B IT efficiency software company. She was responsible for growing its technology team from two people to ...

      (Read Full Article)

      Comment Mentions:   Prelert   Mark Jaffe   Dr. Steve

    4. How Machine Learning Is Improving Computer Security

      Explore smartdatacollective.com (Jul 27 2014)

      The machine learning approach has a major advantage over the more traditional way of threat detection. With the traditional way, systems had to look for signatures that had already been determined to be a threat. Once these signatures were identified within a network, the system would have to either stop it from further infiltration, or eliminate it. This method has some rather obvious weaknesses, the main one being its non-predictive nature. Machine learning is able to address this major weakness by looking through data for certain patterns and signals, thus predicting future attacks and preventing them, letting the system stay ...

      (Read Full Article)

      Comment

  5. Recent Articles

    1. Context Aware Security Analytics Can Save Us

      Explore Lancope (Feb 9 2015)

      No matter how an attacker gains access to your network, they often perform similar actions once they are there. Things like network scanning, privilege escalation, command and control activity, and large data transfers are all common actions that can be identified with the right kind of visibility and analytics.

      (Read Full Article)

      Comment Mentions:   Analytics

    2. Can Security Analytics Replace Humans?

      Explore Security Bloggers Network (Feb 9 2015)

      Initially, we rejected the idea of removing humans from security analysis. However, the further we explored this issue, the more viable it became.

      (Read Full Article)

      Comment Mentions:   Analytics

    3. Gartner: Do You Want “Security Analytics” Or Do You Just Hate Your SIEM?

      Explore Infosec Island (Jan 27 2015)

      Upon some analysis, what emerges is a real problem that consists of the following: 1) Lack of resources to write good correlation rules, tune them, refine them and adapt them to changing needs, 2) A degree of disappointment with out-of-the-box rules (whether traditional or baseline-based) and other SIEM content, 3) Lack of ability to integrate some of the more useful types of context data (such as IdM/IAM roles and user entitlements, as well as deeper asset data), 4) Lack of trust that even well-written rules will let them detect attacker lateral moves, use of stolen/decrypted credentials, prep for ...

      (Read Full Article)

      Comment Mentions:   Gartner

    4. Prelert Expands Executive Team with Key Security Veterans in Response to Increased Demand for Advanced Analytics in the Fight against Cybercrime

      Explore Yahoo! Finance (Jan 20 2015)

      Prelert, the leading provider of machine learning anomaly detection, today announced that it has added two executives to its team in response to the strong demand for its advanced analytics products in the IT security market. Mike Paquette, vice president of security products, and Oleg Kolesnikov, senior director of cyber security and head of security analytics, will reinforce Prelert’s leadership in providing machine learning anomaly detection solutions that can identify advanced threats and data breaches before they result in large data losses.

      (Read Full Article)

      Comment Mentions:   Mark Jaffe   IT Security   Analytics

  6. Recent Comments