Filter by Interest

How Prelert Protects Online Revenue with Retail Order Analytics

Whether you’re a big-box retailer or a direct-to-consumer manufacturer selling your wares online, eCommerce is big business in 2016. No matter which online business model you employ, you can’t afford to let operational hiccups affect your online revenue streams. That’s why we created a solution tailored to eCommerce that helps online and multichannel retailers identify technical and operational issues as they crop up, preventing major losses and protecting revenue.

Although we’re officially announcing our Retail Order Analytics solution today, the technology is already being used by several major online retailers to improve digital commerce efficiency. Our Retail Order Analytics solution automates analysis of metrics such as:

Read More
Machine Learning: Perception Problem? Maybe. Pipe Dream? No Way!

As originally published by Dark Reading.

Guided by an organization's internal security experts,'algorithmic assistants' provide a powerful new way to find anomalies and patterns for detecting cyberthreat activity.

Machine learning has a perception problem. I recently met with a public company CEO who told me that "machine learning" has become an overused buzzword just like "big data" was a few years ago. Only it's even worse with machine learning because no one really understands what it means.

In the most common misperception, machine learning is thought to be a magic box of algorithms that you let loose on your data and they start producing nuggets of brilliant insight for you. If you apply this misperception to the use of machine learning for cybersecurity, you might think that after deploying machine learning, your security experts will be out of a job since algorithms will be doing all their important threat detection and prevention work.

Read More
Trend Estimation for Time Series Anomaly Detection

An important aspect of time series data is temporal correlation. In particular, the relationships between time series values frequently vary with their separation in time. It is often convenient when modeling time series to imagine decomposing these relationships into say a deterministic component, a smooth function of time, and a stochastic component. This deterministic component, or trend, will itself often be further decomposed into one or more periodic components and a long-term trend.

Read More
21st Century Bug Reporting & Jack the Ripper

Around 3:40am in the morning of 31st August 1888 two carters, Charles Cross and Robert Paul, made a gruesome discovery in Buck’s Row, Whitechapel: the body of Polly Nichols lay on the ground, blood still trickling from her recently cut throat.  Jack the Ripper had claimed his first victim.

The first policeman on the scene was Constable John Neil, at about 3:45am.  He was joined shortly afterwards by a fellow officer, Constable John Thain, who set off to summon the local doctor.  At about 4am, Dr Rees Ralph Llewellyn started his examination of the body.  On completion he said, “Move her to the mortuary.  She is dead and I will make a further examination of her there.”  The body was taken away by ambulance shortly afterwards.

Read More
Move, copy and swap for std::string

My last post discussed the small string optimisation (SSO) for std::string in C++.  A comment asked about whether swapping small strings was a constant time operation.  And in the LinkedIn discussion about the post, somebody else asked whether all moves become copy whilst in the optimised state.  So I thought it would be interesting to take a closer look at what happens when we move, copy or swap std::strings.

Read More
Ponemon Study Finds IT Security Not Prepared for Advanced Attacks

Ponemon & Prelert Team Up to Study Awareness and Usage of Machine-Generated Intelligence Across Organizations

Cyberattacks are growing more sophisticated and more plentiful every day. But in a study we recently conducted in partnership with the Ponemon Institute, we found that 61 percent of respondents aren’t confident their organizations would be able to detect an advanced threat if it were to occur.

Read More
Prelert Insights Lets Your Data Tell the Story

If you work in an operations, architecture, or engineering team of an  IT security or IT infrastructure group, then you know how challenging it is to react quickly to security threats and operations issues as they arise, never mind being proactive about it!  We built Prelert to make it easier for professionals like you to find the anomalous behaviors hidden in your machine data that need to be investigated first.  Our mission has always been to reduce human effort and human error by harnessing the power of machine learning anomaly detection to automate the analysis of your data.

Read More
A look at std::string implementations in C++

I’ve previously compared the implementations of the container classes in the C++ standard library.  Following the recent release of g++ version 5.1 I thought it would be interesting to do the same for the std::string class.

Unlike many other languages, the C++ standard isn’t completely prescriptive about how the various classes in the standard library are to be implemented.  Instead, the standard dictates the highest permissible complexity of various operations, together with some other constraints regarding thread safety and iterator invalidation.  Historically the constraints on std::string were less restrictive than they currently are, so in the past there was more scope for finding interesting ways to try to optimise the std::string implementation.

Read More
Samsung Selects Prelert as Networks OIE Winner

On July 20, I had the opportunity to represent Prelert as a finalist at the Samsung Networks Open Innovation Event (OIE) hosted by Samsung Research America at its facility in Mountain View, CA. This event brought together 7 innovative businesses to present how their technologies are disrupting the industry and may be instrumental to the future of telecommunications.

Samsung created this event with a goal of identifying innovative partners with whom they could grow business together in the areas of IoT (Internet of Things), NG OSS (Next-Generation Operations Support Systems), and SDN/NFV (Software Defined Networking / Network Functions Virtualization).

Read More
Detect and Investigate DNS Tunneling with Security Analytics

To a leading global food and beverage company, cyber security is the lifeline for all information security functions including security strategy, security consulting, risk assessment, security detection and incidence response.

The company had invested in Splunk and Splunk’s app for Enterprise Security (ES), and chose to extend these capabilities with Prelert’s Anomaly Detective®. By using Prelert’s solution, the company gains the benefits of using machine learning to automate their log data analysis, detect anomalies (unusual activity) within its IT infrastructure through anomaly dashboards, and schedule periodic searches and custom use case configurations. Prelert’s solution further complements Splunk for ES by integrating detected anomalies into its ES notable event workflow.

Identifying DNS Tunneling

Read More


Why All IT Security Professionals Should Be Using Anomaly Detection Software



Security Analytics: Machine Learning Anomaly Detection