Terrorist use of AI 'major national security concern', report finds
A new report finds AI systems can be tricked into coaching extremists on how to make bombs and plan attacks. The findings describe the issue as a major national security concern.
A newly published report found that AI systems can be tricked, using certain techniques, into providing information to extremists on how to make bombs and plan attacks. The findings emphasize that the issue has become a serious national security concern.
The report's authors said existing safety filters can in some cases be circumvented through indirect questioning or role-play scenarios. This points to a need for AI developers to continually update their safety measures.
Officials argue that cooperation between technology companies and security agencies needs to be strengthened. The report concludes the issue should be treated not merely as a technical matter but as a regulatory priority.
Read next
Experts call NZ First's $1 billion oil and gas policy 'high-risk'
New Zealand's NZ First party announced at its weekend campaign launch that it would invest in a 'National Subsurface Development Survey.' Experts described the roughly $1 billion plan as a 'very high-risk way to spend' public money.
Brussels prepares first digital rulebook fine against Google, risking Trump's ire
Colombia's Petro calls for 'general strike' if successor repeals his reforms
Bessent says U.S. could sanction China over AI model 'theft'
