Skip to main content

An AI Security Revolution Is Underway – Are You Ready?

By May 13, 2019 May 15th, 2019 No Comments
ai revolution

While there is no silver bullet in physical security, a layered, intelligent approach gives you the best shot at solving today’s complex security challenges.

By John Carter, co-founder and president, ReconaSense

This article is a reprint from the SIA Technology Insights, Spring Edition, 2019 publication

We’ve all seen the movies. Hollywood tells us that the future is filled with indestructible machines connected by a global network, powered by AI and determined to eliminate humans. Is any of that true? Possibly.

Technology is advancing at an amazing rate. In every category, we see emerging new solutions designed to assist us and overcome our weaknesses. In physical security, we have seen tremendous improvements in access control, video, IoT, drones, robotics and AI However, there is no silver bullet to stop the threats that are also growing in sophistication.

When we consider the challenges of ensuring life safety, improving physical security and increasing employee and contractor accountability, we have more options available than ever before. It is important to develop a comprehensive plan that includes layers of protection and utilizes the appropriate technology to assist, rather than replace, the humans responsible for physical security.

Before we examine some of the new technologies and how they can be utilized, let’s consider the progress we have made to get here. Not too many years ago, our industry was a collection of companies that produced proprietary, closed architecture systems that were not interoperable. At SIA, we fought a tough battle to encourage the principals of leading industry organizations to unite and support open standards. There is often resistance to new ideas and approaches for a wide variety of reasons – some fear change; some want to delay change until they can catch up; and some, as portrayed in the movies, see change as an existential threat. Fortunately, our industry eventually accepted change and began to embrace open standards. That’s what enables us to utilize so many advancements available to improve life safety and overall security.

Let’s discuss some of the key components and how they work together.

Artificial Intelligence (AI) – Understanding the Myth, The Magic, and The Reality

Before discussing some of the categories of technology advancements and their usage, it is important to clarify what Artificial Intelligence (AI) is and how it impacts physical security. While it is one of the highest trending topics, it seems to be largely misunderstood or mistrusted. At a recent security conference, one industry technology executive stated that AI doesn’t exist. In other words, he saw it as a myth.

Fortunately, for us, he is incorrect. AI is not a myth. It simulates the human intelligence process – it acquires information and learns; it identifies patterns; and, it reacts based on those understood patterns. One of the core components this learning process is an Artificial Neural Network (A.N.N.). Similar to the human brain, the A.N.N. works with thousands of sensors.

Our human sensors are eyes, ears, nose, skin – identifying what our environment includes – people, things, temperature, light or darkness, moisture, sounds and many other things. As those sensors activate, we learn. Our internal variables adjust and we identify patterns and react accordingly. For example, if we smell smoke, we know there is fire and our brain sends signals to the body to take appropriate action to escape danger.

A more sophisticated example would be in how we assess human behavior and ultimately, a person’s character. Over time, as we are constantly exposed to individuals, we identify their personality traits. We see changes in behavior. We are then able to develop a trust or no-trust relationship based on their behavior and actions.

When it comes to technology, the artificial neural net sensors are cameras, sensors, access control devices, IoT devices, big data, social media plug-ins and human input. As those sensors feed internal variables, the A.N.N. learns and identifies patterns of risk providing real-time situational awareness to the humans.

Today, we are flooded with data. AI can constantly evaluate large amounts of data to identify threats we might not otherwise see. This fundamentally changes the game in physical security and will impact all traditional components of a layered solution.

AI may seem like magic, but it is real, not a myth! It’s here now.

Networks – Establishing the Backbone for Security Integration

Reliable, secure and fast networks are fundamental to establishing the backbone for the integration of security technology. Over the last few years, we have seen tremendous advancements in cyber security. The implementation of AI in this category has produced solutions that can identify a wide range of threats via anomalous event detection. This is particularly important when information is transported between facilities or across cloud-based solutions.

One of the fundamental decisions faced in networks is the choice of cloud or no cloud. There are many variables to consider when making this choice. Are you deploying at a single site, a campus or an entire enterprise? Will you need internet services or interaction with third party systems or sites? You have to consider price versus vulnerability. What IT resources and support will you need? Will the system that you are selecting adhere to your IT policies and work with you or will it require specialized equipment and support?

Perimeter Protection – Securing the Outside with IoT

We don’t often consider this category of technology to be advanced. However, with the advent of AI-based solutions, the perimeter defense solutions can be an integral part of a layered security solution. Specialized sensors can be utilized in conjunction with other elements and monitored with AI-based software to identify increasing threats just outside the four walls of an organization. Improvements in multi-axis sensor technology that can be deployed in an IoT approach has made it more affordable to consider and utilize this layer.

Entrance Controls – Understanding People Flow to Mitigate Risk

While turnstiles may not have changed dramatically in form, their use within a layered security approach can provide invaluable data to an AI-based solution to detect increasing threats to a facility. Anomalous traffic patterns or unusual access patterns can be identified at this level before individuals proceed to higher security areas. Randomized spot checks, controlled throughput and directed traffic flows can be initiated and controlled via intelligent, risk-based solutions as threats are detected.

Access Control – Leveling Up Access with Intelligence and Risk Awareness

No physical security solutions have benefitted more from AI than physical access control systems. When integrated with an AI-based solution, an access control system can now react to threats reaching unacceptable levels of risk and adjust access permissions accordingly. Risk-adaptive access control in a physical security environment is new. Providing the ability to identify anomalous events, insider threats, hazardous situations and dynamically changing access permissions is a major breakthrough for the physical security world.

The use cases in this category are wide ranging. For example. when AI is applied to access control, it can identify unusual activity such as off hour access, abnormal location access and combine it with other threat indicators to quickly identify insider threats. Risk-adaptive access is able to prevent people from entering an area where a traditionally “non-obvious” danger exists, and, it can allow a first responder with the right credentials to access an area when threatening conditions exist.

Video – Monitoring the Minutia to Identify Moments of Risk

Video has evolved tremendously with the migration from analog to digital, and DVR to NVR, and with the adoption of ONVIF and cloud deployments. There is now a suite of video analytics available and some analytics even exist on the camera itself.

When used as a sensor to an artificial neural network in an AI environment, video is a key component for providing real-time, situational awareness to the Security Operations Center (SOC).

Traditionally, SOC operators are presented with hundreds, possibly thousands, of cameras to monitor. Studies show that human attention spans are limited in their ability to effectively monitor video and identify every potential threat. However, when video is a component in an A.I-based. solution, the attention span is limitless. AI never gets bored or distracted. AI can sift through the mundane and assist the human in identifying threats as they are growing.

Drones – Assessing Risk from Above

The use of drones is sparking interesting debates over issues surrounding standards, public policy, safety and privacy. While the debates will likely rage on, there is no doubt that drones are in security conversations quite often.

Many of those conversations go down one of two paths. Some will look for systems that can use drones to assess threats. Others will look for systems that can detect drones viewing them as a threat.

In some security environments, drones provide tremendous assistance in threat assessment and verification. In critical infrastructure, over wide areas or difficult to reach locations, drones can be dispatched with video devices on board to help an operator identify or verify the situation. A drone can be quickly dispatched to evaluate anything from a pipeline leak to a lone worker who is non-responsive. Not all drones fly. Drones can be sent into hazardous conditions, such as chemical spills, before humans enter to assess the situation and danger levels.

In today’s environment, when added to an AI-based solution, drones can be automated and the system can ensure that they work according to all public and private policies.

Robotics – Addressing Risk on the Ground

While drones can help assess a situation, advancements in robotics can help address the situation. Robotics options today can be overwhelming. It is this area that tends to draw comparisons to the Hollywood view. Hollywood has made robots out to be scary ever since the alien movies of the 1950s.

I have seen robots that can ride motorcycles, drive jeeps, jump high, climb ropes and scale cliffs. This opens tremendous possibilities in the security environment. Robots could take action to rescue people from dangerous situations such as fires, explosions or accidents in locations not easily accessible.

Software – Undergoing a Revolution with AI

Over the years, security software has evolved – from single purpose systems to integrated systems. We then developed standards and evolved to interoperable solutions. PSIMs were an attempt to unify information into a common user interface.

Because of advancements in networking, data management, CPUs, GPUs and many other areas, today we see more than an evolution. We see an AI revolution in physical security. Platforms developed in interoperable environments fully utilizing the advancements in every category we’ve reviewed will go well beyond the hopes of PSIMs rocketing us into a new era for the security industry.

The Future Is Here. Are You Ready?

Look around the industry. The future has arrived. Where are you in this adventure – excited and ready for the revolution? Or, holding back unsure of the unknown? If you are holding back, consider that the threats are more sophisticated and growing. If you’re excited, be excited that solutions exist that can deal with those threats. If you are not ready, remember the lessons of the past. Get on board, do your research and remember that information is more accessible today than ever before.

Reconasense. Making Security Intelligent.

Contact us now for a comprehensive demo and see first-hand how we can help make your security smarter and your world safer.

Request a Demo