IoT (Internet of Things): Our Future

Life with IoT: 

In just one year alone, we went from having 5 million IoT devices connected to the internet to billions. 

The future is happening now, and these devices are getting smarter every day through machine learning and artificial intelligence. IoT devices are becoming a part of the conventional electronics culture and people are adopting smart devices into their homes faster than ever. It is estimated that there will be up to 21 billion connected devices to the internet. IoT devices will be a huge part of how we interact with everyday objects. There is big money in the IoT space currently, and it will only continue to grow as technology improves. The more data that IoT devices collect, the smarter they will become. Cities will transform into Smart Cities through the use of IoT connected devices. Think of Smart Traffic Lights that collect data on traffic, and use that data to synchronized lights to peak traffic times.

Overall, this improves cities overall efficiency and saves the government money since everything can be remotely managed. Smart homes, thermostats, lighting systems and coffee makers will all collect data on your habits and patterns of usage. All this data will be collected to help facilitate Machine Learning.

How do we security to these devices?

With the billions of IoT devices connected to the open internet, how do we ensure these devices are secure?

Encryption Scheme: AES vs. TLS/SSL

Encryption can solve a complicated problem. When people think about encryption, many will turn to TLS/SSL, however, these protocols don’t cut it for encryption and processing. The reason these protocols aren’t optimal is they are point-to-point solutions and not end-to-end solutions. When data has to go through many different points on the chain, we are going to have to account for different security protocols and devices. This requires a security solution like AES (Advanced Encryption Standard) since it provides end-to-end security, and encrypts the message all the way through. Only devices with the encryption keys can decrypt the encrypted data as it’s sent and received.

AES also allows you to wrap the message body with AES and leave all the actionable data in TLS. Actionable data, for instance, would be temperature information that you are trying to read. In addition, we need to prevent all inbound ports from being open at all costs since this can leave your IoT devices open to vulnerabilities and DDOS attacks. Devices should only make outbound connections, so that way the door is closed to accessing applications and services behind those open ports. The connection outward can be left open so the device can listen in with a secure tunnel back from the network.

Rather than trying to fit all of the IoT Protocols on top of existing architecture models like OSI Model, we have divided the protocols into the following layers to provide some level of organization:

1. Infrastructure (ex: 6LowPAN, IPv4/IPv6, RPL)
2. Identification (ex: EPC, uCode, IPv6, URIs)
3. Comms / Transport (ex: Wifi, Bluetooth, LPWAN)
4. Discovery (ex: Physical Web, mDNS, DNS-SD)
5. Data Protocols (ex: MQTT, CoAP, AMQP, Websocket, Node)
6. Device Management (ex: TR-069, OMA-DM)
7. Semantic (ex: JSON-LD, Web Thing Model)
8. Multi-layer Frameworks (ex: Alljoyn, IoTivity, Weave, Homekit)

Conclude: Machine learning and IoT together can do a miracle in today's modern technology, if both of them are used with good understanding.

AUTHOR:

Mr. NAVNEET VERMA

(Head of CSE Department Geeta Engineering College, Panipat)