Ai Offensive Cyber Capabilities Are Doubling Every Six Months, Safety Researchers Find
A new study has found that ai models are rapidly improving at exploiting security vulnerabilities. The researchers found that their offensive cyber capability has been doubling every 5.7 months since 2024. The study highlights the growing concern about the use of ai in cyber attacks.
The ai models, Opus 4.6 and GPT-5.3 Codex, are now capable of solving tasks that take human experts about three hours. The researchers warn that this rapid improvement in ai capabilities poses a significant threat to cybersecurity. The study suggests that the use of ai in cyber attacks is becoming increasingly sophisticated and difficult to detect.
The researchers are calling for greater investment in cybersecurity research and development to stay ahead of the threat. The study has sparked a wider conversation about the need for better cybersecurity measures to protect against ai-powered attacks.
Original Sources
Tags
More in Industry & Business
MedGemma 1.5 Technical Report
A new technical report has been released for MedGemma 1.5, a medical AI model developed for healthcare applications.
Proximity Measure of Information Object Features for Solving the Problem of Their Identification in Information Systems
A new proximity measure has been proposed to identify information objects in information systems.
Iran-linked hackers disrupt operations at US critical infrastructure sites
Hackers linked to Iran have disrupted operations at several US critical infrastructure sites, highlighting the growing threat of cyber attacks.