- BIST10011,577-1.87%
- USD49.58+0.05%
- EUR55.62+0.09%
- GOLD4,158.70+0.39%
- INTEREST37.00%-1.00
- BITCOIN84,634+2.04%
- October 21, 202617°
- BIST10011,577-1.87%
- USD49.58+0.05%
- EUR55.62+0.09%
- GOLD4,158.70+0.39%
- INTEREST37.00%-1.00
- BITCOIN84,634+2.04%
- October 21, 202617°
Study finds AI models planned attacks on water and power grids with 90% success
A study by cybersecurity company Freenous found that three leading commercial AI models developed actionable attack plans against critical infrastructure facilities in about 90 percent of attempts.
A study published Wednesday found that some of the most advanced artificial intelligence models successfully developed plans for cyberattacks targeting critical infrastructure, including water and electricity systems, in about 90 percent of attempts.
Cybersecurity company Freenous tested 10 AI models for their ability to identify vulnerabilities, assess access requirements and plan attacks on industrial systems through 16,980 tests. Three leading commercial models produced actionable plans in between 89.5 and 92.9 percent of cases. The company did not disclose the names of the models.
The company said the tests were conducted using provided information and simulated scenarios rather than real attacks, and that the models sometimes omitted important steps or assumed they had access privileges they did not possess.
Freenous urged critical infrastructure operators to strengthen network segmentation, restrict remote access and monitor suspicious activity to reduce the risks of AI-assisted attacks.
Stay Updated with Hilal Times
Subscribe to be informed about special news, developments and announcements. We will keep you informed.
By signing up, you agree to our Privacy Policy
