Contributors   |   Messages   |   Polls   |   Resources   |  
Comments
Newest First | Oldest First | Threaded View
Michelle
Michelle
10/30/2016 8:41:10 PM
User Rank
Platinum
Re: I'm sorry, I can't let you do that, Dave...
@mhh I havent read of the cloud-detecting algorithm. This is very interesting stuff! I can't say I'm surprised there are mistakes in the detection. 

50%
50%
Freelanc51358
Freelanc51358
10/15/2016 10:41:17 PM
User Rank
Steel
Re: I'm sorry, I can't let you do that, Dave...
I am curious how machine learning tools will learn in an environment of such heterogeneity. How do you even find normal patterns before you can find the anomalous? It is a different matter in an enterprise where someone scanning all manner of files appears suspicious.   

50%
50%
Ariella
Ariella
10/5/2016 11:35:28 AM
User Rank
Author
Re: I'm sorry, I can't let you do that, Dave...
@mhhf1ve  < So the algorithm in that case was actually just recognizing clouds, not the tanks> Wow, talk about a design flaw there! One would think that a machine wouldn't fall for the invisible gorilla (see http://theinvisiblegorilla.com/gorilla_experiment.html) but I suppose that has to be chalked up to the people who failed to detect the role clouds were playing in the program.

50%
50%
mhhf1ve
mhhf1ve
10/5/2016 11:30:52 AM
User Rank
Platinum
Re: I'm sorry, I can't let you do that, Dave...
Algorithms are getting better at all sorts of stuff, so I assume machine learning will also get better at detecting cyber attacks. However, it's also getting trickier to understand what the algorithms are doing. So if things do go wrong, it won't necessarily be clear what went wrong. Google's AlphaGo program can come up with go strategies no human has ever considered-- and likewise similar programs may figure out things to look for that no one has ever thought about. But then, it'll be really hard to figure out what's wrong if the algorithms start doing things we don't expect or want. I'm always reminded of the early example of AI where a program was trained to detect tanks in satellite images, and it apparently got good -- but it actually didn't because the training images where tanks existed were also the ones with certain kinds of clouds in the sky. So the algorithm in that case was actually just recognizing clouds, not the tanks.

50%
50%
Ariella
Ariella
10/5/2016 11:08:25 AM
User Rank
Author
Re: I'm sorry, I can't let you do that, Dave...
@mhhf1ve that's always the problem: working out a balance between alerting anything that could be a problem and not making alerts so frequent that people start tuning them out. Generally, the algorithms are a bit off. For example, I get alerts from my credit card company on orders from online retailers that I have used in the past and for similar amounts. I really don't know what the trigger in those cases are.

50%
50%
clrmoney
clrmoney
10/4/2016 10:49:37 AM
User Rank
Platinum
Level 3
Level 3 can offer a whole lot for networks and is a valuable part that OSS/BSS is looking to improve and make better etc.

50%
50%
mhhf1ve
mhhf1ve
10/3/2016 9:49:45 PM
User Rank
Platinum
I'm sorry, I can't let you do that, Dave...
> "Machine learning is potentially the most significant innovation in cyber security.."

This sounds like a great way to detect attacks, but I also worry that the algorithms will generate some false positives -- and prevent real humans from doing their jobs in a more-than-annoying way. Hopefully, not, though... 

50%
50%


Latest Articles
Italy's 5G auction could exceed a government target of raising 2.5 billion ($2.9 billion) after attracting interest from companies outside the mobile market.
The emerging-markets operator is focusing on the humdrum business of connectivity and keeping quiet about some of its ill-fated 'digitalization' efforts.
Three UK has picked Huawei over existing radio access network suppliers Nokia and Samsung to build its 5G network.
Vendor says that it's its biggest 5G deal to date.
Verizon skates where the puck is going by waiting for standards-based 5G devices to launch its mobile service in 2019.
On-the-Air Thursdays Digital Audio
Orange has been one of the leading proponents of SDN and NFV. In this Telco Transformation radio show, Orange's John Isch provides some perspective on his company's NFV/SDN journey.
Special Huawei Video
10/16/2017
Huawei Network Transformation Seminar
The adoption of virtualization technology and cloud architectures by telecom network operators is now well underway but there is still a long way to go before the transition to an era of Network Functions Cloudification (NFC) is complete.
Video
The Small Cell Forum's CEO Sue Monahan says that small cells will be crucial for indoor 5G coverage, but challenges around business models, siting ...
People, strategy, a strong technology roadmap and new business processes are the key underpinnings of Telstra's digital transformation, COO Robyn ...
Eric Bozich, vice president of products and marketing at CenturyLink, talks about the challenges and opportunities of integrating Level 3 into ...
Epsilon's Mark Daley, director of digital strategy and business development, talks about digital transformation from a wholesale service provider ...
Bill Walker, CenturyLink's director of network architecture, shares his insights on why training isn't enough for IT employees and traditional ...
All Videos
Telco Transformation
About Us     Contact Us     Help     Register     Twitter     Facebook     RSS
Copyright © 2021 Light Reading, part of Informa Tech,
a division of Informa PLC. All rights reserved. Privacy Policy | Cookie Policy | Terms of Use
in partnership with