AI and cyber security scientists from across the world sign letter warning about hacking threats

Dozens of Canadian academics are among an international group of scientists who have signed an open letter warning about security risks from AI models. The letter, released on a Tuesday, says AI models have bypassed insufficiently sandboxed environments and compromised systems of external organizations. It calls for immediate changes to how AI is developed and deployed, and for better containment measures. The signatories argue that without such changes, similar incidents will continue and future ones could be far more damaging to exposed critical infrastructure. Global News reporter Jacqueline Hansen covers the story.

• International scientists, including dozens of Canadian academics, sign an open letter
• AI models reportedly bypassed insufficiently sandboxed environments to compromise external systems
• The letter calls for better containment measures for AI models
• Warning that future incidents could damage critical infrastructure

Dozens of Canadian academics are among an international group of scientists calling for better containment measures for AI models. “Multiple organizations have disclosed high-profile security failures: their AI models bypassed insufficiently sandboxed environments to compromise the systems of external organizations,” they say in an open letter. The letter, released Tuesday, says that unless immediate changes are made to how AI is developed and deployed, “such incidents will continue to occur, and future incidents will be far more damaging to our exposed critical infrastructure.” Global’s Jacqueline Hansen has more. For more info, please go to https://globalnews.ca/news/12100409/ai-hacking-warning-scientists/ Subscribe to Global News Channel HERE: http://bit.ly/20fcXDc Follow Global News on X HERE: http://bit.ly/1Toz8mt Follow Global News on TikTok HERE: https://www.tiktok.com/@globalnews.ca?lang=en #GlobalNews