Digital fingerprinting is an innovative solution to one of the most common and hardest cybersecurity threats: identity attacks. According to the 2022 Verizon Data Breach Investigations Report, stolen credentials were involved in over 40% of all data breaches, and credential abuse accounted for 80% of all web application breaches. In the age of zero trust, it's not a question of if but when companies will experience an identity attack.
However, security experts believe that Artificial Intelligence (AI) can help identify unusual activities, and with the help of deep learning models, AI can detect potential identity attacks. The director of cybersecurity engineering and R&D at NVIDIA, Bartley Richardson, explains that digital fingerprinting can help detect when someone is not acting like themselves.
His team came up with a deep learning model for every account, server, application, and device on the network to learn individual behavior patterns and alert security staff when an account was acting in an uncharacteristic way.
Security managers agree that it's a big-data problem, and companies collect terabytes of data on network events every day. This means it's good news that cybersecurity and AI efforts are already on their way to combining forces. Richardson’s team used NVIDIA Morpheus, an AI security software library, to build a proof of concept in just two months, and once a crude product was finished, they spent another two months optimizing each portion.
The team then reached out to about 50 NVIDIANs to review their work. Three months later, in early October, they had a solution NVIDIA could deploy on its global networks - security software for AI-powered digital fingerprinting. The software is a kind of LEGO kit that anyone can use to create a custom cybersecurity solution. IT staff can create their own models, changing aspects of them to create specific alerts.
The software works well on major identity attacks, but the team is tuning it with other models to make it more applicable to everyday vanilla security incidents. Richardson imagines that passwords and multi-factor authentication will be replaced by models that know how fast a person types, with how many typos, what services they use, and when they use them.
Digital fingerprinting is not a panacea, but it is one more brick in an ever-evolving digital wall that a community of security specialists is building against the next big attack.
To stay ahead of the curve, security managers need to invest in AI engineering and data science skills.
Meanwhile, Richardson’s team used the software to create a proof of concept for a large consulting firm, which wanted it to handle a million records in a tenth of a second. The team did it in a millionth of a second, and the firm is fully on board.
In today's world, cyber-attacks and data breaches are becoming more common and sophisticated. Identity attacks, in particular, are one of the most difficult to prevent and can cause significant damage to individuals and organizations. However, AI and machine learning are offering new solutions to this age-old problem.
As organizations and individuals continue to face more sophisticated and targeted cyber attacks, it is essential to invest in AI engineering and data science skills to stay ahead of the game. While digital fingerprinting is not a panacea, it is an essential brick in the wall of defense that security specialists are building to protect against future attacks.
Companies need to use every tool at their disposal to combat identity attacks. With digital fingerprinting, companies can use AI to identify unusual activity patterns, and with the help of deep learning models, AI can detect potential identity attacks. Security specialists are continually evolving digital security to counteract the ever-increasing attacks by criminals. Companies should also invest in AI engineering and data science skills, which will help them stay ahead of the curve.
You can try this AI-powered security workflow live on NVIDIA LaunchPad starting Jan. 23. And you can watch the video below to learn more about digital fingerprinting.