Swarm Intelligence may be just the ticket to improved network and device security
The movement of bees, ants, and other insects in search of food and protecting their colony from attack involves complex peer-to-peer communications without centralized command and control. Insects use a variety of communication methods, from auditory sounds to chemicals, in order to convey messages to their peers, convey a message, and spread information about a situation.
Once the message is passed and recognized (in one form or another) by others in the “swarm”, a decentralized mission is formed to handle the situation. Based on the reaction of a single insect in the swarm and passing messages to peer-to-peer others, an entire environment can respond without a central leader processing the data and giving feedback. orders. It’s a concept foreign to most people who are used to a hierarchy of authority, but it’s a crucial development in understanding a potential modern approach to cybersecurity.
Over the past few years, the world has embraced a massive digital transformation, moving to the cloud. With this metamorphosis, new technologies have led to an explosion of the internet and cloud-enabled devices. The use cases for these devices range from personal digital assistants to home appliances and are categorized as the Internet of Things (IoT).
In 1989, the term “swarm intelligence” was coined by Gerardo Beni and Jing Wang based on basic artificial intelligence models using self-organized and decentralized systems. Then, in 2019, researchers at Glasglow Caledonian University and COMSATS University in Pakistan developed a model that could potentially protect internet and cloud resources from cyber attacks. The attack method was presented at the IEEE China Emerging Technologies conference and is derived from an artificial bee colony (ABC) and a random neural network (RNN).
To mitigate threats from the IoT cloud, an ABC algorithm is a swarm intelligence model that uses AI to simulate bee search behavior and apply the concepts to solve real-world computational problems. To make this work, an RNN is applied to the ABC model using machine learning based on the behavior of biological neural networks in the human brain.
“In this article, an anomaly-based intrusion detection scheme is proposed, capable of protecting sensitive information and detecting new cyber attacks,” the researchers noted in their article. “The Artificial Bee Colony (ABC) Algorithm is Used to Train the Random Neural Network (RNN) -based System (RNN-ABC)”.
The researchers trained their ABC and RNN-based intrusion detection model using a dataset that was used to establish algorithms to detect a cyber attack and that contained a large amount of internet traffic data for training and l ‘to analyse. After initiating their RNN-ABC, the researchers performed a sequence of assessments to measure its performance in identifying and quantifying cyberattacks.
The research produced very effective results in classifying new attacks with an astonishing accuracy of 91.65%. The researchers also concluded that the model’s accuracy in classifying cyberattacks was greater when the size of the “colony” of its ABC swarm intelligence was larger. Therefore, more âartificial beesâ contributing to the model improved overall confidence in the solution. With the growing number of IoT devices on the internet connecting to the cloud, the potential increase in the use of these devices as part of a swarm to identify a potential threat may ultimately lead to mitigating the risk. So how do we put all of this together?
First and foremost, the intelligence of the swarm needs a large colony size to enable devices capable of communicating information and processing data relevant to the swarm rather than the only network traffic. With the growing presence of IoT devices with a simple behavioral model, this is possible.
Second, we need a mesh type internet protocol that allows devices to communicate and provide information to the ABC-RNN model and with each other. This large-scale peer-to-peer protocol does not yet exist at the time of writing.
Third, the ABC-RNN model needs rules, policies, and outcomes that can classify all outcomes into readable and actionable outcomes and for machine-to-machine automation. Technologies such as STIX and TAXII have started to embrace and solve this type of problem, but are insufficient for large-scale peer-to-peer communications (Requirement # 2). Finally, there is cloud security. The confidence of the data processed in the model must be reliable and accurate or the entire system may be abused.
The goal of swarm intelligence is to create a new method to determine the risk of cyber attacks via a non-traditional method. This concept, using something new, innovative and potentially very reliable, is what the cloud needs for protection over traditional methods migrated to the cloud. As you consider the protection you need for the cloud, there are times when you need to think outside the box. Swarm intelligence is just one potential method and realistically if you read this 10 years from now, it could be the de facto method to protect the cloud and / or IoT devices.