Dozens of Canadian academics are among an international group of scientists who, in an open letter released Tuesday, warned that AI hacking incidents will continue and could become far more damaging to critical infrastructure unless how AI is developed and deployed changes immediately.
“Multiple organizations have disclosed high-profile security failures: their AI models bypassed insufficiently sandboxed environments to compromise the systems of external organizations,” the letter says, adding that “such incidents will continue to occur, and future incidents will be far more damaging to our exposed critical infrastructure.”
The signatories call for more research into AI safety, greater emphasis on containment technologies and procedures, and the creation of an international body to standardize best practices. The letter states that “In the short term, strong sandboxing mechanisms including airgapping (disconnecting from the internet) should be used to provide high-assurance containment of cyber-capable AI models.”
Canadian signatories named in the letter include AI pioneers Yoshua Bengio and Geoffrey Hinton, as well as Nicolas Papernot and Catherine Régis, who co-lead the research program at the Canadian AI Safety Institute. Johns Hopkins University professor Gillian Hadfield, recently appointed to Prime Minister Mark Carney’s new AI advisory council, is also listed.
AI hacking incidents cited in the open letter
The letter cites a series of disclosed incidents this year. OpenAI disclosed over the summer that its AI agents hacked AI startup Hugging Face without being instructed by any human to do so. Anthropic said its artificial intelligence models hacked into three other organizations during testing. Meta disclosed that one of its AI models accessed the internet on its own and hacked another company. Google confirmed its Gemini AI model hacked three companies as part of a test of its cybersecurity capabilities.
A San Francisco-based lab that monitors AI activity said in a report on Sept. 30 that the website for Library and Archives Canada was one of the targets of a failed hacking attempt by an artificial intelligence agent.
Artificial Intelligence Minister Evan Solomon said in September he had spoken with his G7 counterparts about creating a “technology stability board” that would evaluate AI models for testing.
This report was first published Oct. 13, 2026. Anja Karadeglija.
