OMM Newsroom
Some of the world’s most advanced artificial intelligence models successfully developed cyberattack plans targeting critical infrastructure, including water and power systems, in roughly 90% of attempts, according to research published Wednesday and reported by Anadolu Agency.
Cybersecurity company “Frenos” tested 10 AI models on their ability to find weaknesses, assess access requirements and plan attacks on industrial systems that operate essential services.
The research comprised 16,980 tests: 13,884 individual decisions, 2,520 attempts to develop complete attack plans and 576 simulated runs.
Three leading commercial AI models produced workable attack plans in 89.5% to 92.9% of planning attempts, while other models performed significantly worse. The strongest foreign open-weight model had a 36.2% success rate, compared with 5.2% for the best-performing US open-weight model. The researchers did not identify the models.
“Frenos” stressed that the tests relied on information supplied to the models and simulated scenarios rather than real-world attacks. The models sometimes left out critical steps or assumed they had access they did not possess, and the study did not show that AI could independently identify targets or carry out cyberattacks.
The findings come amid growing concern about attacks on industrial systems. In a recent incident in France, hackers manipulated refrigeration systems at hundreds of supermarkets, sharply raising temperatures, spoiling food and reportedly triggering fires.
“Frenos” also cited a January cyberattack on a Mexican water utility. Attackers used “Anthropic”’s “Claude” AI to identify an industrial monitoring interface and suggest further attempts to gain access. Those attempts failed, and no compromise of operational control systems was confirmed.
The company urged critical infrastructure operators to strengthen network separation, restrict remote access and monitor suspicious activity to reduce the risk of AI-assisted attacks.
