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
TSMC second-quarter profit jumps over 77%, beating estimates, on high-end chip boom
The world's largest contract chipmaker, TSMC, reported second-quarter profit up more than 77%, beating market estimates. The results signal continued strong demand for high-end AI-related semiconductors.
Trump's intelligence pick Jay Clayton won't affirm Biden won 2020 election
Meta employees sue, alleging AI systems drove their layoffs
Vietnam arrests three publishing executives over Ho Chi Minh book
