Humans vs machines: AI and machine learning in cyber security

Artificial intelligence (AI) is at the frontier of a new techno-tsunami that is transforming the way we live and work.

Human vs Technology
Credit: Storm Ventures

“Historically, an AV researcher might see 10,000 viruses in a career. Today there are over 700,000 per day,” says Ryan Permeh, Chief Scientist of Cylance. Could AI be the solution to solving the big data problem, and bridging the widening workforce gap in the Cyber Security industry?

Intelligent machines now have the power to make observations, understand requests, reason, draw data correlations, and derive conclusions. Not only could AI help to effectively detect anomalies and tackle manpower shortage, but it could support rapid incident response operations against zero-day threats.

Is AI the answer to patching all the flaws in our security systems? Or is it making IT professionals redundant? Beyond the hype, any future-proof business must consider the applications and implications of this incoming wave.

The Power of Machine Learning

Traditionally, cyber security has relied on rules-based or signature-based pattern matching. With anti-virus (AV) for example, researchers at AV companies find malware and generate signatures that can be used to check files on an endpoint to see if they match a signature of known malware. This means that one can only detect malware that is known, and that matches a virus definition or signature.

With AI, machine learning can provide an alternative to traditional cybersecurity solutions. Instead of relying on code signatures, machines can analyze the behavior of the programme and use machine learning to find a match, where that behavior is predictive of malicious code. With 2.5 quintillion bytes of data created daily, online platforms constantly have to provide content that is relevant. Netflix does a great job at classifying movie genres and giving movie recommendations. Through machine learning, service providers like Netflix, are able to automatically categorize and offer suggestions by aggregating across the entire database of films and users.

Ability to Detect and Predict New, Complex Threats

Conventional technology is past-centric and depends heavily on known attackers and attacks, leaving room for blind spots when it comes to detecting abnormal events in new-age attacks. The limitations of older defense technologies are now being addressed through machine learning.

For example, privileged activity within an internal network can be tracked, and any sudden or significant spike in privileged access activity could denote a possible insider threat. If it is found to be a successful detection, the machine will reinforce the validity of the actions and become more sensitive to detecting similar future patterns. With larger amounts of data and examples, machines can better learn and adapt to spotting anomalies, more quickly and accurately. This is especially useful as cyber attacks are becoming increasingly sophisticated, and hackers are coming up with new and innovative approaches, of which older security technologies would be slow to detect.

Ease Burden on Cybersecurity Personnel

Machine learning is most effective as a tool when it has access to a large pool of data to learn and analyze from, reducing attack surfaces through predictive analytics. The volume of security alerts that appear daily can be very overwhelming for the security team. Automating threat detection and response helps lighten the load off of cybersecurity professionals who have to contend with prioritizing cybersecurity-related issues and can aid the detection of threats more efficiently than other software-driven methods.

As substantial quantities of security data are being generated and transferred over networks every day, it becomes progressively difficult for cybersecurity experts to monitor and identify attack elements rapidly and reliably. This is where AI can come in and expand their monitoring and detecting operations, making sense of the copious data. Machine learning can help cybersecurity personnel respond to scenarios that they have not specifically encountered before, replacing the laborious process of human analysis.

AI and machine learning also assist IT security professionals in achieving good cyber hygiene and enforces robust cybersecurity practices. The tables are turned as cybersecurity becomes less about an incessant pursuit of hunting down malicious activity, and more about continuous prevention, prediction, and improvement. It could also become a part of the solution for the widening talent gap in the cybersecurity industry.

Limitations of AI and machine learning

One of the greatest challenges would be the adoption of AI technology. For a machine learning engine to perform well, it must retrieve the right data, extract the correct features, and cast the appropriate angle on those features. If trained poorly, it will make inaccurate predictions. Such models are only as good as the data that is fed in. Companies who only do end-point detection are missing out as they lack the data required to leverage on AI.

According to research by Cylance, 62% of security experts believe that there will be an increase in AI-powered cyber attacks in the near future, and therefore, AI may be used as an intelligent cyber weapon. Bad actors could significantly develop their phishing attacks by using AI to circumvent machine learning-based phishing detection systems. In an experiment by Cyxtera, two attackers were able to use AI to improve their phishing attack effectiveness from 0.69% to 20.9%, and 4.91% to 36.28%, respectively.

Seeking Human-Machine Symbiosis

“Cyber attacks aren’t a statistical phenomenon. There is a human attacker behind these threats. We have a living and breathing adversary on the other side of the internet, coming up with new methodologies, daily,” Kevin Lee, Executive Chairman of Horangi Cyber Security.

Many cybersecurity experts have bold opinions on whether machines should be responsible to manage something as complicated as cybersecurity. According to IEEE, human and organizational responsibility for decisions should still be made by the people of the organization and its systems. Refusing to acknowledge the machine’s actions and pushing the liability on them is foolish and could give rise to a regulatory and public backlash.

Only a human can understand the business context of why an attacker might be after a piece of information and what their motivations are. Machine learning is an effective tool against both known and unknown malware, as it can identify and understand malicious activity when applied properly. However, it should not be the only solution. “The combination of human and machine is superior to machine alone or human alone,” said Lee.

Ultimately, the future requirements of cybersecurity are an interplay of advances in technology, legal and human factors, and mathematically verified trust. Effective cybersecurity should be about striking a balance between human and machines. Where computers cannot, humans make sense of the data by ensuring machine-suggested actions have business value too. Humans bring the business, legal, and commercial value into decisions, whilst machines have the capacity and speed to analyze and interpret big chunks of data. Both human intelligence and artificial intelligence must work symbiotically for optimal results. This is the way towards a comprehensive solution that protects against the full spectrum of threats facing today’s businesses.

Estelle Chiu is the Customer Success Manager at Horangi Cyber Security

Source: networksasia


New Technology Can be About Trust

New technology can be about trust, Tendeka director says

Davor Saric-Tendeka
Image Credit:

Digital age, artificial intelligence and machine learning are topics that have been discussed at length by the oil and gas industry.

As the car industry brings autonomous vehicles to the roads, our sector is embracing the advances in all aspects of digital, on a premise of the benefits it can bring.

However, I believe that we already have most of what it takes to be called digitalised.

At Tendeka, we have autonomous inflow control devices (AICDs) that adjust themselves based on the dynamic production environment downhole.

We already have technology that successfully conveys the downhole data to surface wirelessly (award-winning PulseEight technology), we have the cloud-based operating environment (DataServer) and we are working on intelligent algorithms for data analysis that will assist engineers in informed and proficient decision-making.

This will inherently result in more effective day-to-day operations, production and, ultimately, better reservoir recovery. From the reservoir to the point of sale, technology that delivers a significant amount of data from key points of the hydrocarbon recovery system is already present.

In fact, there is an enormous amount of data out there already, neatly collected and stored ready to be analysed. The oil and gas industry has always been a data industry.
What seems to be lacking, especially with data from downhole environments where it matters most for efficient recovery, is manipulation and analysis of that information resulting in a clear, bespoke, fit-for-purpose solution. Solutions may take the form of an automated warning, a visualisation of a trend that prompts an action or an instruction to remotely control the tool that regulates the flow or even an innovation of a new tool.

Whatever the solution, these “decision helpers and enablers” should become an integral part of our engineering workflows.

But can we trust the robot? Can we trust an Artificial Intelligence or autonomous tool to decide and/or control processes and equipment?

Can we put our trust in such technology even if it can result in better and optimised performance, when offset against ever-present risk and high “dollar per barrel” operations?

A recent study found pedestrians are not so comfortable when faced with a prospect of crossing the street in front of autonomous cars.

The solution was the installation of LED screens that mimic the human eyes, which establish an “eye contact” as pedestrians cross in front.

The results of repeated study showed greatly improved trust and confidence. We are aware that autonomous vehicles will improve road safety and quality of life, but our acceptance of it still depends on our perception, confidence and risk.

I believe that the oil and gas industry is not so dissimilar.

We need to learn to trust innovative digital solutions and innovative tools to deliver more effective energy recovery from our planet.

Of course, trust is not a given, but with proven data, in-depth understanding and an open mindset to new techniques, our industry should embrace innovation and change.

The benefits will speak for themselves.

Davor Saric, technology director, Tendeka

Written by Davor Saric – 08/11/2018 6:00 am

Digital life stories spark joy in people with dementia

I was sitting on the sofa across from Christine in her home. She offered me a cup of coffee. Each time I visited, she sat in the same spot — the place where she felt most comfortable and safe. She had shared stories from the past and decided to talk about the birth of her daughters, grandchildren and great grandchildren.

For Christine, a research participant in a multi-sited study into dementia and digital storytelling, the fear dementia brings is that she won’t be able to be a part of special moments such as the celebration of birth.

As we worked together in Edmonton, creating a multimedia story from her memory, Christina started to remember new things. She became emotional when she talked about her daughters becoming mothers themselves. She pointed out that the project was so much more powerful than looking through a photo album. Like many participants, she said she recalled stories she hadn’t thought about for years.

As a post-doctoral fellow in occupational therapy under the supervision of Dr. Lili Liu, at the University of Alberta I worked with several participants in this study. Funded by the Canadian Consortium on Neurodegeneration in Aging, one of our goals was to investigate quality of life and how technology affects the lived experiences of persons with dementia.

Technology and quality of life

In this research project we defined digital storytelling as using media technology — including photos, sound, music and videos — to create and present a story.

Most previous research on digital storytelling and dementia has focused on the use of digital media for reminiscence therapy, creating memory books, or enhancing conversation. Collaboratively creating personal digital stories with persons with dementia is an innovative approach, with only one similar study found in the United Kingdom.

During this project, I met with seven participants over eight weeks. Our weekly sessions included a preliminary interview to discuss demographics and past experiences with technology. Then we worked on sharing different meaningful stories, selecting one to focus on and building and shaping the story. This included writing a script, selecting music, images and photographs and editing the draft story.

“I was blessed with wonderful parents, and I was a mistake,” begins Myrna Caroline Jacques, 77, a grandmother of five.

Participants worked on a variety of topics. Some told stories about family and relationships, while others talked about a particular activity or event that was important to them. After all participants completed their digital stories, we had a viewing night and presented the stories to family members.

Happiness in the moment

It was an intense process. Eight sessions working one-on-one with persons with dementia required a significant amount of thinking, remembering and communicating for the participants. There were challenges, such as when participants found themselves unable to express their thoughts or remember details.

In this digital story, Christine Nelson talks of her love for her children and her fear of forgetting special moments.

Although many participants were tired after a session, they all felt that it was a beneficial and meaningful activity. Working in their homes on a personally gratifying activity with a tangible outcome seemed to keep them motivated and eager to continue. The process was also enjoyable and gave the participants something to look forward to each week.

There was a sense of happiness in the moment. And the way that participants responded to me, along with their ability to remember who I was and the purpose of our sessions, all indicated a deeper positive connection. The participants all felt a sense of accomplishment and family members were proud to see the end product at the viewing night.

Into the future

I have met with one of the research participants again recently, and she still remembers me. I would like to follow up with the others to get a sense of the long term impact of this digital storytelling project. I am also eager to see how the findings in Edmonton line up with those from the studies in Vancouver and Toronto.

For the participants, talking about memories helped them open up about having dementia. Getting past the fear and looking ahead with optimism was the message I heard, and one that I hope to keep hearing.

Originally Written on: