Posts Tagged ‘security’

Digital Reasoning Takes On Early Risk Detection For Compliance- And Security-Sensitive Sectors

synthimageDigital Reasoning’s Synthesys machine learning platform (which The Semantic Web Blog initially covered here) this summer should see its Version 3.9 release. The update will build on the 3.8 release, which delivered with its Glance user interface the discovery and investigative capabilities that help information analysts in finance, intelligence and other compliance- and security-sensitive sectors react to findings in user profiles of interest and their associated relationships, activities and risks. Version 3.9 takes on the proactive part of the equation — early risk detection — via its Scout user interface.

Last year, the company honed in on compliance use cases ranging from insider trading to money laundering with Version 3.7 of Synthesys (covered here). There, the technology for discovering the meaning in unstructured data at scale, highlighting important entities in context, was applied to email communications for organizations such as financial institutions that have to be on the lookout for conversations that cross compliance boundaries.

Read more

Machine Learning Part Of New Versium Solution To Quickly Find Fraudsters

versiumMachine learning is playing a role in fraud prevention: This week Versium launched its Predictive FraudScore solution to help companies weed out fraudsters from signing up for their services or conducting ecommerce transactions with them. All the organization needs is an email address.

The solution is based on Versium’s LifeData predictive analytics platform that also is behind the company’s churn, social influencer, shopper and custom scoring products. “There are three fundamental areas we bring to fraud scoring: unique data, powerful matching technology to identify and associate that data to accounts or consumers as they sign up, and applying machine learning to that unique data set to predict whether that account is likely to be associated with fraud or not,” says Versium’s CEO Chris Matty.

The FraudScore service provides an enterprise a very strong indication of whether a person is legitimately interfacing with it at the point in time that that entity registers with the company. “That’s quite upstream from where normal fraud prediction takes place,” Matty says.

Read more

10 Considerations for Securing the Internet of Things

10447375095_03bde7458d

Mark O’Neill, VP of Innovation at Axway recently wrote for Silicon Angle, “Welcome to the future, where smart meters monitor your home appliance usage, where fitness devices on your wrist track your heart-rate, and where electric vehicles can take commands from your wristwatch. What does all of this have in common? These innovations are all part of the Internet of Things (IoT). While the Internet of Things is going through a rosy honeymoon period at the moment, security issues are slowly creeping to the surface. There’s a growing awareness that IoT devices are riddled with vulnerabilities, and securing these weaknesses will soon become one of the major priorities for both manufacturers and the people who use them. Let’s examine the top 10 things to consider in detail.” Read more

Machine Learning Predictive Analytics Take On Hacks, APM And More

rsz_prelertpixLast week the world learned that the hacks at Target hit more customers than originally thought – somewhere in the 100 million vicinity – and that Neiman Marcus also saw customer credit card information spirited away by data thieves. They’re not the first big-name outfits to suffer a security setback, could they be the last?

No one can ever say never, of course. But it’s possible that new tools that leverage machine learning predictive analytics could put a serious dent in the black hats’ handiwork, while also improving IT’s hand at application performance management.

A big problem in both the APM and security space today is that there’s just a ton of data coming at IT pros dealing with those issues, much of it just describing the normal state of affairs, and no one’s got time to spend reviewing that. What IT staffers want to know about are problems, which leads to a lot of rules-writing to identify thresholds that could point to issues, and to a lot of rewriting of those rules to account for the fact that things change fast in today’s world of system complexity – and to a lot of misses because of the impossibility of keeping up. Sixty percent of problems are still reported by users, not the tools IT is using, says Kevin Conklin, marketing vp at Prelert, whose machine learning predictive analytics technology is used in CA’s Application Behavior Analytics and available as Anomaly Detective for the Splunk IT apps ecosystem.

Read more

Make Enterprise Search Better For Users, And Better For IT

rsz_searchHow seamlessly are employees able to conduct searches for enterprise data?

According to a new survey from SearchYourCloud, not very. Some searches, it finds, take up to 25 minutes, and often users have to do 8 different queries until the right document is found. Only 1 in 5 searches come out with correct results the first time. “That’s appalling in this day and age,” says founder and CEO Simon Bain.

Read more

Riskified Helps Stop E-Commerce Fraud with ‘Semantic Risk Engine’

Carmel Deamicis of Pando Daily reports, “Dr. Eyal Kishon, co-founder of Israeli based venture capital firm Genesis Partners, had a very personal reason for investing in Riskified, a startup that fights fraud for e-commerce sites. He kept getting rejected when he’d try to buy things online. Merchants would occasionally flag him as a “risky” purchase — perhaps because he lived in Israel and American stores can’t fact-check international addresses through the Address Verification System (AVS). Israeli startup Riskified, which recently raised a $1.65 million seed round, thinks its “semantic risk engine” is the answer. The technology builds a story around the shopper that ties together two types of information — the transaction information (where the person’s shipping address and billing address are, what proxy server they’re hiding behind, etc) and publicly available information about the person online. That way, they can more accurately predict which online shoppers are fraudsters and which are legitimate.” Read more

Privacy Reforms and Web TVs

Liat Clark of Wired reports, “The European Commission is off-track and will stifle innovation with its data protection proposals because it’s only just catching up with web 2.0, a term coined in the 90s, according to James Leaton Gray, head of information policy and compliance at the BBC. He issued this warning at the Westminster eForum seminar on eprivacy, flagging up the impracticalities of the proposed reforms, pointing out that the future of computing is in your TV — and the proposals aren’t taking this into account. ‘It makes me extremely nervous,’ said Gray. ‘If you look at IPTV, you’re connected to the internet and directly to thousands of TV channels across the world. The present remote control will become a search engine — it won’t be things you type into, it will be about the semantic web, accessing and exchanging data. The idea that it’s confounded to computers and a computer-based world is a fallacy’.” Read more

Carnegie Mellon Researchers Release Details of Automatic Video Surveillance Tech

Declan McCullagh of CNET reports, “Computer software programmed to detect and report illicit behavior could eventually replace the fallible humans who monitor surveillance cameras. The U.S. government has funded the development of so-called automatic video surveillance technology by a pair of Carnegie Mellon University researchers who disclosed details about their work this week — including that it has an ultimate goal of predicting what people will do in the future. ‘The main applications are in video surveillance, both civil and military,’ Alessandro Oltramari, a postdoctoral researcher at Carnegie Mellon who has a Ph.D. from Italy’s University of Trento, told CNET yesterday.” Read more

Experian Acquires Garlik, Ltd.

Today, Experian, the global information services company, announced that it has acquired Garlik Limited, a provider of web monitoring services based in the United Kingdom. Garlik uses Semantic Web Technologies to help consumers protect themselves from the risks of identity theft and financial fraud.  At the last SemTechBiz UK Conference, Steve Harris, CTO of Garlik, presented “Combatting Online Crime with RDF.” Mr. Harris presented a compelling case of Garlik’s use of Semantic Technology throughout its offerings to support business-critical, highly sensitive production systems to financial institutions worldwide. Read more

An RDF based Permissions Model

GatesOne of the primary challenges in putting together a good content management system is building a decent permissions model. Whether a particular user or process is able to perform some kind of an action upon a resource or not can be remarkably difficult to establish, especially when there are multiple constraints involved. For an XML-based CMS, this can be even more of a challenge, because the n-dimensional nature of such a constraint model is often difficult to model in hierarchical structures.

However, RDF is far more ideally suited for this particular role. A permissions system is, at its core, a set of assertions about who can do what to what, which fits nicely with the “subject predicate object” model that RDF exemplifies. Moreover, because such models are sparse — the number of assertions is likely to be very small compared to the total potential assertions that are possible — this fits nicely into models where sparseness of data is a common characteristic (again, RDF), as compared to storing this information (expensively) in tabular fields as with a relational database.

I’m working on building an XML-based CMS (specifically on a MarkLogic platform, though I would like to keep it portable), and realized as I was working on it that while the user permissions system that MarkLogic employs is powerful, it’s not portable and there are facets that don’t fit nicely into that particular model. Thus, I decided to chase the RDF triples approach to see if that would work better for this. (The end product may very well be a hybrid approach to take advantage of fast queries, but that’s beyond the scope of this particular article).

Read more

NEXT PAGE >>