What is Machine Learning?
Machine Learning is an application of Artificial Intelligence.
The idea of Machine Learning basically is based upon the premise that we can make a machine (usually a computer) to learn from some massive amounts of data, so that it can make predictions when it is presented with new data.
The machine would perform automated sequencing of data and comb through whole data and trying its best to search for patterns... Once it reaches to the point where it has identified most patterns and can make predictive behaviours, it (or technically speaking, its algorithm) applies some certain rules to accomplish its objectives. However, it should be capable of modifying exists rules (made by you or human-entities), also of creating new rules itself.
What you need to remember is that this machine or system should be capable of IMPROVING itself with more and more experience. If it cannot do that, then it is not capable of learning new stuff, by itself. Put another way, machine learning teaches computers to do what people do: learn by experience.
We as humans are capable of learning from our past experiences to make present or future decisions, we are expecting the same or very much similar from ML. Technically speaking, it is the same reason that makes ML different from statistical models, such as Linear Regression.
Across all fields of knowledge & science, people have been using Linear Regression to establish the relationship between variables and response, and to make predictions based on the existing data-set. The predictions made by regression-models may be precise up to an extent only and beyond that extent, those will be extrapolative in nature and precision is usually lost. Moreover, statistical models don’t use training data to learn, and predictive accuracy is not their strength.
-
Important Conditions for Machine LearningA few conditions are necessary for ML to operate properly:
1. Data
The relevant data must be consolidated and accessible. Data includes text, images, computer clicks and social media postings.
2. Algorithm
An algorithm must be developed to analyze the large amounts of data for similarities and patterns. Enough computational processing power must also be available for the program to comb through vast amounts of data.
3. Rules
A basic set of rules must be provided to the machine to serve as guidelines.
-
Machine Learning & Human InterventionIt is obvious that ML algorithms easily beat humans, because of their computational speed and capacity. You already know that computers can analyze massive amounts of data and recognize patterns much more quickly than humans ever will.
Humans, however, are still the major driving force as you would be defining and setting the rules the algorithms follow, while analyzing and learning from past data to make decisions or recommendations. The objectives of the algorithms, too, are set by humans, and it’s up to you to ensure the algorithms are used in ways that promote rather than endanger human values. It is something that can never be bargained with...
-
The Role Of Machine Learning in CybersecurityWithin the context of cybersecurity, the ultimate hallmark of using Machine Learning is to achieve the ultimate capabilities offered by 'Automation.'
Today the threat-landscape for each organisation is so vast that you have no choice but to constantly track and correlate millions of external and internal data points across your infrastructure and your users. It simply is not feasible to manage this volume of information with only a team of people that you may have.
This is where machine learning may become exceptional, because it can recognize patterns and predict threats in massive data sets, all at machine speed. By automating the analysis, your cyber teams can rapidly detect threats and isolate situations that need deeper human analysis.
Let us consider the following scenarios in cybersecurity where you are going to see the impact of Machine Learning :
1. Finding threats on a network
Machine learning can detect threats by constantly monitoring the behavior of your network for anomalies. Machine learning engines can process massive amounts of data in near real time to discover critical incidents happening there in your organisation. These techniques allow for the detection of insider threats, unknown malware, and policy violations in your company.
2. Keeping people safe when they are browsing
Machine learning can predict “bad neighborhoods” on internet to help prevent your users from connecting to malicious websites. Machine learning can analyze Internet activity to automatically identify attack infrastructures that are capable of launching current and emergent threats.
3. Providing malware protection to endpoints
ML Algorithms can detect even unknown-threats too if they are attempting to run on your endpoints. It already can identify new malicious files and activity based on the attributes and behaviors of known malware.
4. Protecting your data in the cloud
Machine learning can protect your productivity & performance by analyzing suspicious cloud apps' login activity, detecting location-based anomalies, and conducting IP reputation analysis to identify threats and risks in cloud apps and platforms.
5. Detecting malware in encrypted traffic
It can detect malware in encrypted traffic too by analyzing encrypted traffic data elements in common network telemetry. Rather than decrypting, machine learning algorithms pinpoint malicious patterns to find threats hidden with encryption.
6. Generating Next-Gen of Threat Intelligence
The real advantage of ML is about time and context.
Machine Learning is capable of taking millions of webpages together, extracting the content from code, surpassing the human-language barriers, reading the lines (codes) of files, parsing the logs, correlating attack-vectors with IOCs, or malware categories, so thousand things more...Machine Learning is capable of building a thorough CONTEXT around all sorts of threats and can even potentially predict what would be the next stage of any attack facing your organisation.
The resultant Threat-intel would be highly sophisticated and more accurate than current threat-intel you have access to till now. It would succeed in highlighting the specific vulnerabilities, exploits, or actors you should be focusing on.
7. A Quantum Leap in Incident Response Capabilities
The secret to actionable threat intelligence lies in playing to the individual strengths of machines and human analysts. The future of cybersecurity isn’t about man OR machine — it’s about man AND machine. Machines would perform the heavy lifting (data aggregation, pattern recognition, etc.) and provide a manageable number of actionable insights. From there, human analysts make decisions on how to act.
-
Kindly write 
your comment on the posts or topics, because when you do that you help me greatly in 
designing new quality article/post on cybersecurity.
your comment on the posts or topics, because when you do that you help me greatly in designing new quality article/post on cybersecurity.You can also share with all of us if the information shared here helps you in some manner.
This Article Was Written & published by Meena R, Senior Manager - IT, at Luminis Consulting Services Pvt. Ltd, India.
Over the past 16 years, Meena has built a following of IT professionals, particularly in Cybersecurity, Cisco Technologies, and Networking...
She is so obsessed with Cybersecurity domain that she is going out of her way and sharing hugely valuable posts and writings about Cybersecurity on website, and social media platforms.
30,000+ professionals are following her on Facebook and mesmerized by the quality of content of her posts on Facebook.
If you haven't yet been touched by her enthusiastic work of sharing quality info about Cybersecurity, then you can follow her on Facebook:
Click Here to follow her: Cybersecurity PRISM