The Active Shooter Epidemic: One Major Preventive Measure Launching Today
By: Anil Chitkara, President & Co-Founder, Evolv Technology
Too many mass shootings.
Too many venues without security checkpoints.
Too few technology solutions identifying the individuals who require a closer look.
Too many conversations with security professionals and venue operators asking for something better.
At Evolv, we have had enough. The “new normal,” as some have called it, is unacceptable. We’ve dedicated ourselves to keeping people safe by using technology to stop active shooters. The safer world we envision should be something that everyone simply expects without having to think about it.
Six years ago, Mike Ellenbogen and I started Evolv Technology with a mission to save lives.
Prior to the founding of Evolv, we spent more than two years conducting research. We met with security professionals across the globe and developed a deep understanding of modern threats and what security professionals need to prevent mass casualty events. We visited university labs and small tech companies to understand the latest innovations in sensors, data synthesis, image reconstruction, machine learning, and design thinking. Then, leveraging our combined 40+ years of experience using technology to solve critical, complex problems, we started Evolv.
At Evolv, we set out to solve a very tough problem: how do you recognize that the vast majority of people pose no threat, while simultaneously identifying those few who may be a threat and require a closer look. It’s a simple problem statement, but a difficult question to answer.
Our First Product: Evolv Edge
We launched the Evolv Edge system in 2017, after about 3 ½ years of research and development. Evolv Edge is one of a kind. It’s the first product in the industry to screen people and their belongings at high speed without requiring them to stop or remove items from their pockets and bags. From a technology perspective, Edge’s combination of sensors, signal processing, detection algorithms, and user-centered design is like nothing else on the market. Gone are the white bowls for your keys, coins, wallets, belts and cell phones; gone is the need to stop and put your hands in the air. There is no need to place your bag on a table for a guard to search prior to walking through the Edge. With the Edge, you just walk through.
Since its launch, the Edge has screened more than 25 million people around the world, primarily at entertainment venues, sports stadiums, tourist locations, workplaces, hospitals, and houses of worship. In that time, the Edge has detected more than 5,000 weapons. Prior to selecting the Edge, many of these venues tried walk through metal detectors, but found the experience for their visitors to be too slow and cumbersome. These outdated pieces of equipment also resulted in long lines, creating a potentially new security target and concern.
Feedback on the Evolv Edge has been very positive. We’ve seen first-hand the reactions of visitors going through the system and guards operating it. The most common question we are asked is “Why don’t they have these everywhere?”
What We’ve Learned
As we deployed the Edge and spoke to thousands of security professionals and venue operators, we again asked how we could advance screening technology to make many more venues even safer, while continuing to deliver a positive visitor experience. These conversations were enlightening. We heard significant concern about several different scenarios:
- Workplace Violence Prevention:
One of the biggest areas of concern was the proliferation of workplace violence. People should not be concerned for their safety while at work. Many employers, however, are not willing to put a traditional checkpoint in place. They are looking for a system that screens people with little-to-no inconvenience.
- Event Screening:
Another scenario we heard was about screening large crowds for events. The shootings in Las Vegas, Gilroy and Jacksonville Landing highlight the need to screen large numbers of people at special events.
- Tourist Screening:
The third scenario we continued to hear was around screening at tourist locations. Many of these locations, whether an observation deck, museum, or landmark, carry their own unique complexities. Many visitors are carrying food, clothing, cameras, and a host of other personal items for a day’s outing. Often there are international visitors speaking a range of languages.
These three scenarios were just a few of the many that were highlighted.
In many cases, security teams had tried traditional checkpoints with walk through metal detectors and found them to be unsustainable solutions. Traditional screening created massive lines, frustrating visitors or employees, and resulted in an unacceptable overall experience. These stories, which we continue to hear on a daily basis, inspired the design for our newest product.
Introducing Evolv Express
We’re now launching our second product, Evolv Express™. Whereas the Edge screens individuals one-at-a-time as they pass through the system for venues who want a control point, Express screens large groups of people at a time with no stopping, no emptying of pockets or removing bags. After eighteen months of development, we’re now releasing Express, the fastest threat screening product on the market that ensures every individual and their belongings are screened as they pass through without even breaking stride. We have incorporated the latest high-speed sensors that move data in real time to a detection algorithm that renders a decision as people pass through; with Express, 60 people can be screened every minute, that’s 3,600 per hour. The system screened more than 250,000 individuals during our pilot testing this spring and summer. As with the Edge, Express detects those individuals who require a closer look, and automatically alerts guards and security personnel to confirm those individuals are not a threat.
How Express Works
Evolv Express combines the latest technologies and user-driven design principles to provide this high throughput, truly frictionless approach to screening thousands of people per hour. It all starts with the brains of our system, the Evolv Cortex AI Software Platform™. This is a machine learning-based AI system that uses data sets we have generated from the system to train the algorithm. The training is conducted on a methodical basis, starting with a designated threat set, such as firearms. A range of threats is scanned, and classifiers are developed, refined, tested, tuned, and hardened to detect the threat set. Similarly, a range of non-threatening items such as cell phones is scanned through the system. A similar approach is undertaken to create classifiers. As the range of threats and non-threats are analyzed by our development team, the algorithm is continually refined. Over time, as new threats emerge and data is collected, the algorithm will continue to be refined. This process is done in our labs in a controlled manner. Once we are confident in the performance of each new algorithm, it will be released and upgraded to Express systems operating at customer sites.
A key Express component is the sensors that collect data to drive the algorithm. These sensors were designed by Evolv to optimize the separation of the signals for both threat and non-threat items. After scanning millions of people with the Evolv Edge system, we had developed a tremendous body of knowledge regarding sensors as well as the typical items that are carried by visitors through our systems. This body of data informed the design for the Express sensor set.
We have also optimized the data flow through our system. For each individual screened, the Edge system moves nearly 1 million data points to the algorithm, with a resulting red light / green light decision as the person exits. For Express, this ultra-high speed data-processing engine has been further optimized to render a decision in less than one second from the time a person starts walking through.
A significant amount of time was spent on the Express user experience. The UX has a number of components: the industrial design of the system, the interaction with visitors being screened, the operator’s interaction with the system, and the people moving and setting up the system. Each of these elements has been carefully thought through and tested with the respective user group.
- Industrial Design:
The Edge was a significant step forward in designing a system that is welcoming to people passing through it. We have taken some of those key design elements and made improvements to streamline the look even further. Additionally, we recognize these systems need to visually fit into the environment, so we added the ability for users to add custom branding or signage on a key component of the system.
- Visitor Experience:
We widened the overall design to make it easier for people to pass through with minimal disruption.
- Operator Experience:
Our focus on the operator experience has resulted in a system that is easy to operate as thousands of people pass through each hour. There are a mix of audio and visual cues for the operator. If an individual alarms, there is a picture of the person alarming, with the alarm location clearly outlined for further evaluation.
- Ease of Deployment:
Finally, a key element of the system is the ability to move it around to enable screening at different locations. The system has built-in mobility capability, for easy breakdown, movement, and set-up. When the system is powered on, an automatic software calibration routine runs through diagnostics, resulting in the system being up and operational in two minutes.
We are starting a roadshow to preview the Express to security professionals around the U.S. Next week we will be unveiling at the ASIS GSX Security Show in Chicago. After that, we will be in major cities around the U.S. And, you will start to see the Express working at venues around the country keeping people safe.
We set out to solve a very tough problem: how do you recognize that the vast majority of people pose no threat, while simultaneously identifying those few who may be a threat and require a closer look; how do you improve public security without disrupting the public? Over the past 6 years we’ve dedicated our resources and our expertise to answering these questions.
We’re humbled to have the opportunity to ‘make our dent’ in the universe and couldn’t be more excited to launch Evolv Express.
What Role Can Technology Play in Building and School Security?
By Christian Wilson, MarketScale – August 12, 2019
Building security continues to be an increasingly important issue for business owners and building managers. Over the last decade, everywhere from commercial office buildings to retail centers and college campuses have been subject to violent attacks taking place within their walls.
With a wave of modern technology taking over workplaces in America, building managers are beginning to utilize things like Artificial Intelligence and facial recognition software to improve security measures and as a result help save lives.
While smart security systems have played an important role on the ground, many companies are exploring how to better secure premises’ from buildings’ immediate airspace using unmanned aerial surveillance, more commonly known as drones. Security firms like Nightingale Security offer a Robotic Aerial Security Service that provides clients with drones to provide a new-level of aerial surveillance.
There are several benefits corporations can gain from drone security. This service utilizes drones for autonomous patrol missions, autonomous threat response, and manual surveillance missions. This application can be critical not only for quick response to a significant event like an oil spill, break-in or locating a trespasser, but also helps security officers on the ground have a quick and reliable perspective of the events with a birds-eye view.
Advancements in building security have been especially imperative for school districts nationwide. On this front, every second is critical when it comes to assessing a threat and protecting the safety of countless children and staff. While most schools have some sort of security team and camera infrastructure in place, the Putnam County School System in Oklahoma has gone above and beyond. It has invested $10 million over the last four years, and in a recent major upgrade, installed facial recognition software in its security camera systems.
According to KFOR News in Oklahoma, “Campus police plan to use the system to track a short list of people prohibited from entering the building. The software allows users to input a “watch list” of suspects, that is, anyone who’s not supposed to be in the building. In practice, the cameras with facial recognition are able to positively identify an intruder within 15 seconds of entering the building. Within 30 seconds, campus police are aware of the presence of the suspect.”
The main purpose of this is to add an extra layer of security to ensure people like ex-employees and their spouses, expelled students, or runaways don’t cause any harm or distractions in a place they aren’t supposed to be.
The high-capacity data processing power AI holds translates into big implications for large-scale access and crowd control. Companies like Evolv Technology offer physical security systems comprised of an AI-powered screening system working alongside facial-recognition to help enhance security and ease accessibility for patrons in places like sporting events and airports.
The systems are set-up at a checkpoint in a building and the video surveillance uses machine learning algorithms to match a face placed on a “watchlist” from the cameras. The system even has predetermined threat levels set for individuals on the watchlist. For example, if a red flag is displayed on an unauthorized person, they are immediately located, detained, and removed from the property. If a person brings up a yellow flag, meaning they are an undetermined threat, a person is physically dispatched to monitor the person and make a determination on a proper course of action. The company claims this process takes a matter of seconds.
This technology can help make patrons in large crowds feel safer, keep staff in these high-volume areas better prepared, and help mitigate bottlenecks and long-lines so many are accustomed to in large crowds.
Technology is Driving Modern Security
Now more than ever there is a renewed sense of urgency for companies and building managers to make sure the people occupying these buildings -are the safest they can be. The marriage between data, surveillance, and security has proven to have some serious benefits behind it. There are, however, still challenges these security firms face in this new era of security. The balance between personal privacy and general security has and will continue to spark debate and it is up to those in charge of security to make sure no line is crossed at the expense of someone’s privacy. In the meantime, any advancement in security is a needed one because at the end of the day, the better the technology in a building, the safer people inside of it will be.
Why I Started Evolv: A Q+A with Co-Founder and CEO, Mike Ellenbogen
By Melissa Cohen, Vice President of Marketing –
I recently sat down with Mike Ellenbogen, our CEO and co-founder. We discussed his career path, what’s to come in the security industry in 2019 and Mike’s advice for aspiring entrepreneurs. See what Mike had to say.
Melissa Cohen: Mike, you have a lot of experience launching new companies and building something from the ground up based on a new idea. You did this with both Evolv and your previous company. Can you tell us about an accomplishment that shaped your career?
Mike Ellenbogen: Absolutely. I love building things and always have. I had a eureka moment that triggered the inception of my first company, Reveal Imaging. After new legislative requirements for airport security screening were put in place following September 11, I realized it made sense to employ smaller, less expensive systems and connect them together via a network of PCs. We rethought the way checked baggage was screened in the U.S., considering the total cost of the systems as opposed to just the cost of the technology. Ultimately, Reveal Imaging was acquired by Science Applications International Corporation (SAIC) in August 2010. I’m immensely proud of the work that team did and grateful for the experience – it’s really helped shape who I am today and is what motivated me to keep going and start Evolv.
MC: Based on your extensive experience in the security business, what do you think makes a good CEO in the industry?
ME: There needs to be an inclination to push beyond the conservative approach that is so common in the security industry. There are plenty of businesses out there with the “same old” security technology that’s been around for decades. I like to push the envelop and ensure that my company is offering something that solves a problem while also surprising and delighting. I think it’s important that a security industry CEO sees the world that can be rather than replicating what’s already out there or being happy with the status quo.
MC: What’s the biggest challenge you’ve faced in building either of these businesses and how did you overcome it?
ME: The core technology at both companies was/is really complicated – millimeter wave imaging is a challenging field, so is Artificial Intelligence (AI). Of course, you have to have technology that works in order to have repeatable and reliable customers that you can pursue. Leading an emerging technology company and inventing fundamentally new technology, there’s inherently a lot of pieces you have to glue together. It’s daunting and the success of the company is reliant on a deep understanding of the physics of the real world and how to appropriately push the boundaries of electronics and processing.
With any new technology or applications, there is also a steep learning curve among your teams. An engineer may be familiar with the technology, but not with the application. On that note, another challenge is finding the kind of people that can help move the physical security technology industry forward. We look for people with credibility, who have energy and creativity, and can also help move the needle.
MC: What are some of the biggest trends and themes you’ll be watching for in the security industry in 2019?
ME: We’ll definitely see further integration of AI and facial recognition into more security technologies and applications. Disparate AI capabilities will need to be packaged in a way that is more useful for customers in 2019. We’ll also see an increase in compute power at the edge, for example, more compute power within security cameras rather than via a central/integrated service. And, I know people have been saying this outside of the security industry for years, but we’re going to see expanded use of the cloud and Software as a Service (SaaS) within security technologies. While this has already started, some major shifts in this space are coming.
MC: Let’s do some rapid-fire, fun questions. How would you describe your leadership style?
ME: I like to think I present a vision of what could be to get people behind that vision – you need people to believe in the vision to engage them in getting there. Considering I’m focused on solving problems in a new way, I also recognize that it’s important for me to surround myself with people who are optimistic but real.
MC: What is your top productivity hack?
ME: I live my life multi-threaded, which I think is just another way of saying that I’m always trying to be efficient. I do a lot of different things in parallel. For example, I turn the coffee pot on before I get ready for work so that it’s ready when I leave. I take pride in maximizing my time like this.
MC: What piece of advice would you give your younger self?
ME: I always wanted to run a company and invent something – this desire was within me from a very young age. I would tell myself you need time to see the opportunities in the market, so find an industry you really love, make it your own, and word incredibly hard at it.
MC: What motivates you?
ME: Every day I’m motivated by the vision that the technology we’re working on is important and helping to save lives. As I mentioned before, I also love building new things and, in doing so, helping to bring success to the people around me.
MC: What best practices can you share for future leaders who are looking to start a business?
ME: It’s all about the people. Whatever your path, you’ll be spending a lot of time in the trenches with them, so you better like them. And of course, expect the unexpected!
AI’s Role in the New-World Security Paradigm
By Michael Ellenbogen, CEO, Evolv Technology –
It’s no secret that artificial intelligence (AI) is exerting its influence on society in profound ways. AI can be found pretty much everywhere – in applications ranging from self-driving cars to online assistants to game-playing computers to the prediction of judicial decisions. It’s solving problems, moving markets and changing lives.
AI is also weaving its way into the realm of physical security. While its uses are still evolving, AI is positioned to play a key role in the new-world security paradigm, where terrorist attacks and mass shootings have broadened the threat landscape and made it more unpredictable. Security responses are shifting from reactive to proactive, and vendors are integrating AI technologies into some of today’s security solutions. Here are three AI applications that can help organizations take a proactive security approach to prepare for future threats.
Determining what’s “normal”
Before you can declare that a situation is abnormal and worth attention, you need to be able to define “normal.” Using machine learning, an advanced form of AI, computers can be taught how to identify an object once certain characteristics are specified. Once the computer learns what a normal environment is, it can monitor for anomalies and alert security personnel when it identifies something out of the ordinary.
More specifically, computers can be taught what is allowed in a certain area at a certain time. For example, a system can be taught that figures moving around outside a public building are normal during the day but abnormal at night. When an environment changes from normal to abnormal, an alert can be automatically triggered.
Using AI, computers can do more of the work of monitoring environments, giving guards and operations personnel more bandwidth to focus on higher priority tasks, such as quickly responding to an actual threat. Automating monitoring of these environments also reduces human error.
Understanding when a threat is really a threat
So, now that AI is helping to define what’s “normal,” it can go to work determining what constitutes a “threat.” Machine learning can be taught to identify an object as something specific based on certain characteristics. This is referred to as “object recognition.” It can be used to identify outliers to the norm – which, in a security context, can be defined as threats.
For instance, in the situation above, security personnel want to be alerted at night if a specific type of figure enters the scene. People obviously qualify as potential threats. Perhaps some large animals or vehicles would be worthy of an alert. Small animals? Birds? Windblown trash? These would be picked up by some sensing systems, but they’re not actual threats. If a computer can be taught to recognize certain objects by their size, shape or specific actions, it can flag threats and filter out benign activity.
With the right sensors, when surveying a large crowd of people, guards can determine if a visitor’s bag might contain a threat object and then track that visitor or object. Should that person appear back on the screen without the bag, the computer can search the environment for the item, quickly sending security guards to that specific area and clearing the crowd.
In a security checkpoint scenario, this application drastically reduces the need for hand wanding or physical full-body pat downs as the technology itself can alert guards if someone is carrying an item of interest. Guards can then focus on a subset of people as opposed to screening thousands of visitors or travelers with the same level of rigor – which would improves the visitor experience for all involved.
Tracking objects in video feeds
Tracking a figure based on characteristics is advanced; re-identifying the figure without using facial recognition takes security to a whole new level. This technique, referred to as “object re-identification,” is used to track an individual through multiple fields of view from different cameras. With law enforcement teams often working from blurred and obscured images when identifying a suspect, this emerging capability is extremely promising despite its current limitations.
Being able to track someone or something by its shape, clothing or gait could best be described as a game-changer for security operators. Using AI, law enforcement could, in theory, track a known threat and detain a suspect before he commits an attack. However, performance improvements in faceless detection are still needed as false match rates continue to run high.
AI + IQ
While AI’s adoption is helping organizations and security professionals proactively prepare for future attacks, it can’t do this alone. It has the power to analyze data quickly and identify patterns, but it can’t necessarily determine if these patterns are relevant. AI needs help from the kind of real, grounded intelligence that only humans can provide. Using the combined power of AI and human intelligence, security teams can truly arm themselves to fend off emerging threats.
Read more here about how AI will impact the airport.