Iot & AI

The future when people will come home after work and ask their TV to turn on and the washing machine to wash clothes in the economy mode doesn’t seem so distant.

We can already talk to virtual assistants like Google Home, Siri or Alexa to search for a movie or order a new scarf with delivery at door. Why not doing the same thing with everything else?

In fact, this is what everyone now calls the Internet of Things which is according to Wikipedia basically the network of physical devices, vehicles, home appliances, and other items embedded with electronics, software, sensors, actuators, and connectivity which enables these things to connect, collect and exchange data. For any IoT service to be worth buying, such actions must demonstrate true value and yield benefit to the user. Of course, they vary from adequate physical actions (e.g. deploying a taxi to the site) to simply informing users (e.g. sending a message to inform a user that they have run out of milk).

It is here at the data analysis step that the true value of any IoT application is determined, and this is where Artificial Intelligence provides a crucial role by making sense of data streamed from devices. AI serves to detect patterns in this data from which it can learn to adjust the behavior of IoT service.

Probably the best example of AI and IoT successfully working together is self-driving cars by Tesla Motors. Cars act as “things” and use the power of Artificial Intelligence to predict the behavior of cars and pedestrians in various circumstances. Moreover, all Tesla cars operate as a network. When one car learns something, they all learn it.

Automated vacuum cleaners are a good example of artificial intelligence “embodied” in a robot. For example, iRobot by Roomba controlled through an app can map and “remember” a home layout, adapt to different surfaces or new items, clean a room with the most efficient movement pattern, and dock itself to recharge its batteries.

Another good example of AI and IoT combined together is a smart thermostat solution by Nest Labs. Nest’s smartphone integration allows to check and control temperature from anywhere. The device analyzes temperature preferences and work schedule of its users and adapts temperature accordingly.

Applications, where IoT works together with AI, are only growing, creating new markets and opportunities and they are highly unlikely to lose ground in the nearest future.

The Internet of Things is getting smarter. Companies are incorporating artificial intelligence—in particular, machine learning—into their IoT applications. The key: finding insights in data.

With a wave of investment, a raft of new products, and a rising tide of enterprise deployments, artificial intelligence is making a splash in the Internet of Things (IoT). Companies crafting an IoT strategy, evaluating a potential new IoT project, or seeking to get more value from an existing IoT deployment may want to explore a role for AI.

Artificial intelligence plays a growing role in IoT applications and deployments. Both investments and acquisitions in startups that merge AI and IoT have climbed over the past two years. Major vendors of IoT platform software now offer integrated AI capabilities such as machine learning-based analytics.

The value of AI in this context is its ability to quickly wring insights from data. Machine learning, an AI technology, brings the ability to automatically identify patterns and detect anomalies in the data that smart sensors and devices generate—information such as temperature, pressure, humidity, air quality, vibration, and sound. Compared to traditional business intelligence tools—which usually monitor for numeric thresholds to be crossed—machine learning approaches can make operational predictions up to 20 times earlier and with greater accuracy.

Other AI technologies such as speech recognition and computer vision can help extract insight from data that used to require human review.

In its essence, the technology of IoT is about devices with built-in sensors, which provide data to one or more central locations through internet connectivity. That data is then analyzed and corresponding actions are initiated. AI applications for IoT enable companies to avoid unplanned downtime, increase operating efficiency, spawn new products and services, and enhance risk management.

AVOIDING COSTLY UNPLANNED DOWNTIME

In a number of sectors—industrial manufacturing or offshore oil and gas, to name two—unplanned downtime resulting from equipment breakdown can cost big money.

Predictive maintenance—using analytics to predict equipment failure ahead of time in order to schedule orderly maintenance procedures—can mitigate the damaging economics of unplanned downtime. Machine learning makes it possible to identify patterns in the constant streams of data from today’s machinery to predict equipment failure. In manufacturing, Deloitte finds predictive maintenance can reduce the time required to plan maintenance by 20–50 percent, increase equipment uptime and availability by 10–20 percent, and reduce overall maintenance costs by 5–10 percent.

INCREASING OPERATIONAL EFFICIENCY

AI-powered IoT can also help improve operational efficiency. Just as machine learning can predict equipment failure, it can predict operating conditions and identify parameters to be adjusted on the fly to maintain ideal outcomes, by crunching constant streams of data to detect patterns invisible to the human eye and not apparent on simple gauges.

Machine learning often finds counterintuitive insights: A shipping fleet operator’s machine learning tools determined that cleaning their ships’ hulls more often—an expensive, downtime-causing process—actually increased the fleet’s overall profitability. The math went against shipping industry instincts: Hulls kept smooth through frequent cleaning improve fuel efficiency enough to vastly outweigh the increased cleaning costs.

ENABLING NEW AND IMPROVED PRODUCTS AND SERVICES

Enhancing IoT with AI can also directly create new products and services. Natural language processing (NLP) is getting better and better at letting people speak with machines, rather than requiring a human operator. AI-controlled drones and robots—which can go where humans can’t—bring all-new opportunities for monitoring and inspection that simply didn’t exist before.

Fleet management for commercial vehicles is being reinvented through AI, which can monitor every measurable data point in a fleet of planes, trains, trucks or automobiles to find more efficient routing and scheduling, and reduce unplanned downtime. Cloudera claims its fleet management AI has cut downtime for fleet vehicles monitored by Navistar devices up to 40 percent.

ENHANCING RISK MANAGEMENT

A number of applications pairing IoT with AI are helping organizations better understand and predict a variety of risks as well as automate for rapid response, enabling them to better manage worker safety, financial loss, and cyber threats.

Applications already in use include detecting fraudulent behavior at bank ATMs, predicting auto driver insurance premiums based on their driving patterns, identifying potentially hazardous stress conditions for factory workers, and monitoring law enforcement surveillance data to identify likely crime scenes ahead of time.

IMPLICATIONS FOR ENTERPRISES

For enterprises across industries, AI is a natural complement to IoT deployments, enabling better offerings and operations to give a competitive edge in business performance.

Machine learning for predictive capabilities is now integrated with most major general-purpose and industrial IoT platforms, such as Microsoft Azure IoT, IBM Watson IoT, Amazon AWS IoT, many more

A growing number of turnkey, bundled, or vertical IoT solutions take advantage of AI technologies, especially machine learning. It is often possible to use AI technology to wring more value from IoT deployments that were not designed with the use of AI in mind. IoT deployments generate huge, constant streams of data, which machine learning excels at examining to identify patterns that lead to greater value.

THE FUTURE OF IoT IS AI

It may soon become rare to find an IoT implementation that does not make some use of AI. The International Data Corp. predicts that by 2019, AI will support “all effective” IoT efforts and without AI, data from the deployments will have “limited value.” If your company has plans for implementing IoT-based solutions, those plans should probably include AI as well.

The Internet of Things (IoT) is a term that has been introduced in recent years to define objects that are able to connect and transfer data via the Internet. ‘Thing’ refers to a device which is connected to the internet and transfers the device information to other devices. The cloud-based IoT is used to connect a wide range of things such as vehicles, mobile devices, sensors, industrial equipment’s and manufacturing machines to develop a various smart systems it includes smart city and smart home, smart grid, smart industry, smart vehicle, smart health and smart environmental monitoring. In the IoT, cloud computing environment has made the task of handling the large volume of data generated by connecting devices easy and provides the IoT devices with resources on-demand.

An increasing number of physical objects are being connected to the Internet at an unprecedented rate realizing the idea of the Internet of Things (IoT). A recent report states that “IoT smart objects are expected to reach 212 billion entities deployed globally by the end of 2020”. Similarly, while the number of connected devices already exceeds the number of humans on the planet by over 2 times, for most enterprises, simply connecting their systems and devices remains the first priority. A recent report state that, “The overall Internet of Things market is projected to be worth more than one billion U.S. dollars annually from 2017 onwards”. As a result, data production at this stage will be 44 times greater than that in 2009, indicating a rapid increase in the volume, velocity and variety of data.

Hence, IoT based smart systems generate a large volume of data often called big data that cannot be processed by traditional data processing algorithms and applications. Here will therefore, by difficulty in storing, processing and visualizing this huge data generated from IoT based system. However, there is highly useful information and so many potential values hidden in the huge volume of IoT based sensor data. IoT based sensor data has gained much attention from researchers in healthcare, bioinformatics, information sciences, policy and decision makers in governments and enterprises. Nowadays, Artificial intelligence methods play a significant role in various environments including business monitoring, healthcare applications, production development, research and development, share market prediction, business process, industrial applications, social network analysis, weather analysis and environmental monitoring.

The IoT and Artificial Intelligence (AI) will play a vital role in numerous ways in the future. There are multiple forces which are driving the growing need for both technologies and more and more industries, governments, engineers, scientists and technologists have started to implement it in manifold circumstances. The potential opportunities and benefits of both AI and IoT can be practiced when they are combined, both at the devices end as well as at server. For example, AI combined with Machine learning can study from the data to analyze and predict the future actions in advance, such as order replacements in marketing and failure of equipment in an industry just in time. Moreover, AI can be used with machine learning in smart-homes to make a truly grand smart home experience. Similarly, AI methods with IoT can be used to analyze the human behavior via Bluetooth signals, motion sensors, or facial-recognition technology and to make the corresponding changes in lighting and room temperatures. This special issue aims to gather recent research works in emerging artificial intelligence methods for processing and storing the data generated from cloud-based Internet of Things.

Threat intelligence in enterprises

A threat intelligence is a fairly new concept still evolving as product / service where the concept is to gather raw data about existing or emerging threats and threat actors from several sources, and then analyzes and filters that data to produce usable information in the form of management reports and data feeds for automated security control systems. Its primary purpose is to help organizations understand the risks of and better protect against major threats specifically zero-day threats. We can tune the service to deal with advanced persistent threats and exploits, especially those most likely to affect their specific environments.

Learning about relevant threats as soon as possible gives organizations the best chance to proactively block security holes and take other actions to prevent data losses, breaches or system failures.

Threat intelligence service models

Threat intelligence service companies like ITS, we are relative newcomers to this section of security industry, so there are still a lot of differences among the types of services each vendor delivers.

Some such services simply provide data feeds that have been cleansed of most false positives. The most common for-a-fee services provide aggregated and correlated data feeds (usually two or more), as well as customized alerts and warnings specific to a customer's risk landscape. Another type of threat intelligence service handles data aggregation and correlation; incorporates information automatically into security devices (firewalls, security information and event management, etc.); and provides industry-specific threat assessments and security consulting.

Many types of threat intelligence platforms are sold on a subscription basis, usually at two or three capability levels, and is delivered via a cloud platform. We at India Training Services offer managed services for delivery across on-premises systems. This comprises of training and a solution installed on cloud platform for the enterprise as one Threat Management solution.  

Threat intelligence platforms can dramatically improve the efficiency of security staff in proactively blocking security incidents, because subscription costs tend to run moderately high to very expensive, and because of the equipment needed for on-premises deployment, threat intelligence platforms are currently geared mainly toward larger midmarket organizations and enterprises. As the cloud continues to move down market, however, threat intelligence tools are bound to do likewise.

The history of threat intelligence

Threat intelligence solutions or platforms came into being mainly because of the plethora of data available, whether generated internally or acquired from external feeds, on current and emerging IT security threats. It takes considerable time, effort and expertise to sift through the data and transform it into information that's pertinent to an organization, however.

Security companies, such as Symantec, that make it their business to track threats and provide frequent updates to their antivirus products, have maintained global threat databases for years,  populated from software agents running on millions of client computers and other devices. Such data, along with feeds from other sources, is the foundation for the information provided by developed threat intelligence tools.

Understanding threat intelligence service data

Data from various threat intelligence sources differs in quality and structure, and must be validated. Validating data involves human and machine analysis for processing, sorting and interpreting.

Apparent threats are also correlated against the entire pool of threat data to identify patterns that indicate suspicious or malicious activity, and are also linked to technical indicators for categorization purposes. Finally, the data is converted into contextual information that provides insights about the tactics and behavior patterns of emerging or advanced threats and threat actors.

In the end, the threat information that's usable and actionable must be accurate, timely, relevant to the customer, align with the customer's security strategies and be easily incorporated into existing security systems.

Characteristic features of threat intelligence solutions

Now that we've understood the purposes and benefits of threat intelligence, let's look at the most common features found in these kinds of services.

• Data feeds: Many types of data feeds are available through threat intelligence platforms. Examples include IP addresses, malicious domains/URLs, phishing URLs, malware hashes and many more. A vendor's threat intelligence feeds should draw data from its own global database, as well as from open source data, information from industry groups and so on, to produce a pool of data that is both broad and deep.
• Alerts and reports: Most services provide real-time alerts, along with daily, weekly, monthly and quarterly threat reports. Intelligence may include information about specific types of malware, emerging threats, and threat actors and their motives.

Security analysts or IT security staff members are needed to manage data feed information. The data is either incorporated into proprietary equipment (typically from the same vendor that provides the feed), or the information may be available in standard file formats, such as XML, CSV, STIX or JSON, for use in a variety of security management tools and platforms.

Depending on the level of information in the data feeds, staff might need specialized or specific training from the vendor.

Some companies offer managed security services that offload most of the administrative burden associated with a proactive security approach. A managed service may include experts that provide threat intelligence reports, monitor an organization's assets 24/7 and provide threat mitigation and incident response.

The cost of threat intelligence platforms varies as much as the services themselves. Data feeds alone can cost thousands of dollars per month, and related expenses include the costs of maintaining a 24/7 security operations center staffed with technicians and analysts. By way of comparison, managed security services are typically tens of thousands of dollars per month, easily running into six or seven figures per year for larger environments.

As with most things in business, the least expensive services require more human time and effort on the customer side.

Because threat intelligence services vary widely, a key challenge in selecting such a service is knowing what the organization needs on what is the most critical information to maintain, how the information will be distributed / used and having the right staff in place to use that service appropriately.

There a large number of threat intelligence services out there, and they all deliver and collect data about emerging threats in different ways. Some are better at providing detailed global threat reports, while others are capable of drilling down and delivering reports to customers that are highly industry- or (even) company-specific. In addition, there are some services that better serve an organization with existing defense equipment, while others provide threat intelligence that's easily integrated into an organization's existing security controls -- no matter the equipment in place.

We deliver a range of training courses carefully designed to help people and organizations protect themselves against crippling data attacks. We can tailor a specific training module to meet your needs, or you can contact me at ravindrapande@gmail.com.

Also we have pre-developed modules on Threat Intelligence planning

·         Developer Security Training

·         QA Security Test Testing Training

·         Mobile Penetration Testing Training

·         Wireless Penetration Testing Training

·         Security Awareness Training

·         Web Application Penetration Testing Training

·         Infrastructure Penetration Testing Training

Visit us at www.indiatrainingservices.com