Breaking News
Fetching data...

Wednesday, 1 March 2017

How AI will lead to self-healing mobile networks


How AI will lead to self-healing mobile networks



Today we are routinely awed by the promise of machine learning (ML) and artificial intelligence (AI). Our phones speak to us and our favorite apps can ID our friends and family in our photographs. We didn’t get here overnight, of course. Enhancements to the network itself – deep, convolutional neural networks executing advanced computer science techniques – brought us to this point.
Now one of the primary beneficiaries of our super-connected world will be the very networks we have come to rely on for information, communication, commerce, and entertainment. Much has been written about the “networked society,” but on this transformative journey, the network itself is becoming a full-fledged, contributing member of that society.
AI and ML will propel networks through four stages of evolution, from today’s self-healing networks to learning networks to data-aware networks to self-driving networks.

Stage I: Self-healing networks ­– “I know what happened”

Today’s networks are in Stage I – a real-time feedback loop of network status monitoring and near real-time optimizations to fix problems or improve performance. The sensory systems and the network optimizations are based on human-made rules and heuristics using simple descriptive analytics. For instance, if signal A goes above threshold B for C seconds, initiate action X.
These rules are typically easy to interpret but are suboptimal to modern, data-driven alternatives because they are hard-coded, cannot adapt to changing environments, and lack the complexity to effectively deal with a wide range of possible situations. In fact, these rules are limited by the inability of the human mind, even an experienced and intelligent mind, to find all the meaningful correlations affecting network KPIs among a massive data set of influencing factors. They also don’t allow the humans responsible for network performance to anticipate trouble, making “real-time” the limiting factor to an optimally-performing network.

Stage II: Learning networks ­– “What will happen?”

Timing is everything. Stage II networks will continuously find patterns in past network data and use them to predict future behavior. ML can be directed to analyze factors thought to be impactful, like time/day, network events, or one-time or recurring external events or factors (e.g. an election, a natural disaster, or a trend on YouTube).
The value in the data lies in probabilistic correlations between past network performance and manual solutions that provide future optimizations. ML can capture as many correlations as model complexity allows, with data scientists and domain experts working together to best separate signal from noise, calibrating and testing ML models before they are put into production. ML models can reveal an exhaustive distribution of network KPIs and a dizzying array of external influencing factors, and then expose the subtlest of correlative relationships for the sake of predicting future outcomes.
These predictions give human overseers advanced warnings of how to distribute network resources and perform other optimizations, leading to enhanced performance at lower cost. For example, a network ‘autopilot’ could detect the slightest predicted deviations from the optimal path and issue warnings to human operators long before actual problems emerge. Continuously collecting data and comparing predictions against reality will enhance accuracy, leading to better next-gen models.
ML methods of note for Stage II include linear and non-linear supervised methods, tree-based ensembles, neural networks, and batch learning (e.g., retrain overnight). In Stage II, predictive assistance means more time for human operators to effect change, and the result is a breakthrough in network performance. Machines make predictions, and humans find solutions, with time to spare.

Stage III: Data-aware networks ­– “What should I do?”

The student becomes the master. By Stage III, AI algorithms review past performance and, independent of human direction, identify undiscovered correlative factors affecting future performance outside the guidance of human logic. They do so by looking beyond network data and initial guidance into external data sets such as generated and simulated data.
Machines use knowledge obtained from supervised methods and apply that knowledge to unsupervised methods, revealing undiscovered correlative factors without human intervention or guidance.
A Stage III network provides predictions of multiple possible futures and creates forecasts allowing management to predict potential business outcomes based on their own theoretical actions. For example, the network could let human managers select from a set of possible future outcomes (highest-possible performance during the Super Bowl, or lowest-possible power usage during holiday hours). Thus begins the era of strategic network optimization, with the network not only predicting a single future, but offering multiverse futures to its human colleagues. ML methods for Stage III include deep learning, simulation techniques, and other advanced computer science techniques like bandits, advanced statistics, model governance, and automatic model selection.
While highly capable, a Stage III network is still not technically “intelligent.” That grand jump towards the Singularity occurs in Stage IV.

Stage IV: Self-driving networks – “Just do it.”

I reason, therefore I am. A Stage IV network can (1) independently identify and prioritize factors of interest that impact network performance, (2) accurately predict multiverse outcomes in time for optimally executed human-effected remedies, and, most importantly, (3) distinguish between those factors that are causal vs. correlative to gain deeper insights and drive better decisions.
The distinction between causal and correlative is itself based on probabilistic analysis as seen in research. The ability of AI to establish causality is the ability to understand the root causes of network performance as opposed to the correlative signs of those causes. The ability to identify causal factors will lead to more accurate predictions and an even better-performing network. At this stage, the network gains the ability to reason cause vs. effect – and the truly intelligent network is born.
A Stage IV network can autonomously choose a course of action to maximize operational efficiency in the face of external influences. It can improve security against new incoming threats and more generally operate to maximize a given set of KPIs. The system is adaptive to real-time changes and continuously learns and improves in a data-driven context. ML methods of note for Stage IV include deep learning, reinforcement learning, online learning, dynamic systems, and other advanced computer science techniques.

Network, heal thyself

The notion of applying remedies at locally before globally is apropos in the case of AI and ML. While the world will no doubt benefit greatly from the democratization and mobilization of its ever-expanding mountain of data, it is the network and the networked society that stand to benefit the most, soonest, from our journey towards the truly intelligent machine.

Read more

Saturday, 25 February 2017

Crash Your Friends WhatsApp With A Special Secret Message


Crash Your Friends WhatsApp With A Special Secret Message 2016



This tutori
al is all about Whats App and in this tutorial we are Going to show you that how to crash whats app application of your friends and this process is very Easy and the best thing about this tutorial is that you can crash the Whats application with a Single Secret message.
During the time of tutorial if you find any queries, then please feel to ask us by simply commenting in the comment box and we will get to you ASAP.

Things You Need:-
  • Android device(with Active internet connection)
  • Secret message here
Step 1: Open WhatsApp and then Select your Victim’s Number.
Crash Your Friends WhatsApp
Step 2: Open the Special Message from the link above.
Step 3: After opening the message Link, tap on Raw and then copy the whole message and then paste it 4-5 times in the message box and then send it to your victim, Voila You did it.
You can Do the same thing with an application known as WUB. Download WUB from here.
Crash Your Friends WhatsApp
Step 1: After installing the application, open it and Fill maximum number of emojis in text part and in the Amount part write 5000.
Step 2: Tap on Generate and send and choose the victim’s Number and then Send.
Crash Your Friends WhatsApp
Note: This Crash may not work on some device. I have personally tested this it works Fine. Every tutorial in gadgetsay is for educational purpose, we are not responsible for any loss.

Read more

The Attack of the Alerts and the Zombie Script


The Attack of the Alerts and the Zombie Script

In our previous post we found a way to UXSS (bypass the SOP policy) using the htmlFile/ActiveXObject, however, I mentioned that there were other interesting things to do using that same object. Have you tried anything? If yes, congratulations. The only way to find bugs is by trying, and today we are going to explore another interesting thing that can be done with the same ActiveXObject.
Have you noted recently that all browsers have a feature to block perpetual alerts? As soon as you execute a second alert it comes with a check-box to disable the following ones, just like this:
This gives us (bad programmers) the chance to exit never ending alert-loops, but more important, it allows the user to defend himself against malicious pages that literally block the interface with fake messages. Users have now the chance to block all the following alerts by checking that box, but with the ActiveX window object we can continue throwing infinite alerts with no way to escape them.
If you haven’t read the previous post about the UXSS using htmlFile/ActiveXObject, please do it now. It’s important to understand why we are using specific members of this htmlFile/ActiveX (like how to get its window object). Anyway, let’s use the alert method from the ActiveXObject which completely bypasses the preference of the user of “no more alerts please!”. We can throw infinite ones but for this demo we will do it with just three.
Honestly, I’m not impressed at all. Yeah yeah, unlimited alerts but it’s no big deal considering that other security researchers are bypassing DEP / CFG and re-enabling the God Mode. Let’s try something better. We will throw a few alerts but all visible at once, filling the entire screen with thousands them! No worries, in this PoC we will use just ten!

See the PoC Live on IE11 ]

Wow! This is not impressive, but it will keep the user and those amazing researchers busy . Click click click 🙂 . I know alerts are not interesting and let’s be honest, once the user has a chance to leave the page, he will be free from our horrible alerts, right? Wrong! We can be persistent and continue running our code even after he left our page. Imagine a user who goes to Google trying to escape from us, but continues to receive our alerts! Hehe 🙂 Let’s do it, it’s not hard at all.

Persistent Code

In order to make our code persistent (or a zombie script as some people call it), we need to keep a reference to the object that runs the script and make a call the window.open method. Those two things will make IE think it should not destroy the object because there’s still a reference to it. The good thing is that the reference can be in the object itself!
  1. Save a reference to the ActiveXObject.
  2. Use the window.open method.
Just one more thing: keep in mind that using the window.open method does not mean that we need to literally open a window/tab. In fact, we will use a very simple/old trick which apparently does nothing: window.open into the same window with an empty URL.
That’s it! Now the user can type anything in the address-bar, click on links or navigate as much as she wants, but our script will always be with her until the tab is closed. And by the way, everything here can be done straight from inside an iframe on a different domain, and still work (without bypassing SOP, of course).

See the PoC Live on IE11 ]

Wow! This is amazing! The setInterval keeps running even after leaving our page! Navigate, try it by yourself! Is there a way to combine the previous UXSS with this bug and have UXSS everywhere? Can we know where exactly the user is or the URL in the address bar? Check out this video where I was just teasing Eric because of a Twitter conversation that we were having.
Tip: the window.open trick that we did is useful for other things too. For example, if we run it against the top window (not matter how deeply framed we are), then, IE thinks the main window was opened with scripting and it allows us to close it without confirmations, just like this:
Have a nice day full of passion, bug hunter!
by Amit
Read more
 

latest posts

Contact Form

Name

Email *

Message *