- The US government is creating a virtual environment to test machine learning and AI methods to combat cybercrime.
- As artificial intelligence is being integrated into more and more parts of our lives, certain agencies are using it to combat crime.
- More and more finance-focused companies are integrating machine learning and artificial intelligence into their systems to gain a competitive edge.
The use of artificial intelligence is getting more and more popular with it appearing in the financial sphere specifically. Machines are able to perform and learn from data by themselves without being programmed to do so with machine learning. Following that, especially after the pandemic, the need for automated systems has been at an all-time high.
The research plan
The Science and Technology Directorate (S&T) and the Cybersecurity and Infrastructure Security Agency are working together to create a virtual environment that uses machine learning to combat cybercrime. In this artificial environment, researchers will test machine learning and artificial intelligence methods to see how well they can analyze cyber threats and serve as tools in the battle against them.
The research plan of the project consists of three main topics as follows:
The development of a multi-cloud “sandbox” environment enables active experimentation, which will serve as the next-generation training environment.
Tools and tradecraft
Studying data analysis techniques and technologies, especially those that use artificial intelligence, AI, or machine learning, ML.
Automating the machine learning loop
The ML solution loop will be built and automated using CAP-M, and after that, the operations (such as data exporting and tweaking) through the loop will also be automated.
Data gathered will be shared
The Science and Technology Directorate wrote that information acquired from the tests will be distributed to other people in the government, academic settings, and the corporate sector. The article also stated that they will take privacy concerns into account. While initially supporting cyber missions, the CISA Advanced Analytics Platform for Machine Learning (CAP-M) will include a multi-cloud environment and multiple data structures with the environment also being adaptable for other infrastructure security missions.
Sami Elhini, biometrics specialist at Cerberus Sentinel, did raise security concerns by saying,
« When using ML and AI to identify patterns and exposing those models to a larger audience, the probability of an exploit increases (…) Adversaries quickly learned that by introducing noise into face images that was imperceptible to humans, they could fool face recognition systems to produce a false non-match. »
There was no timetable provided for the project’s completion.