Cyberattack AIs must be trained only on air-gapped systems, hundreds of AI researchers say
487 AI researchers, including Hinton and Bengio, urge air-gapping cyber-capable models and a new international safety body.
An open letter signed by 487 AI researchers, including Geoffrey Hinton and Yoshua Bengio, says current training safeguards are inadequate for cyber-capable models. The signatories call for air-gapping, stronger sandboxing, more safety research, and a new international body to set standards and receive reports of containment failures. The appeal goes further than recent remarks by Microsoft president Brad Smith and an ongoing UK parliamentary look at AI security.
- 487 researchers signed, including Geoffrey Hinton and Yoshua Bengio.
- Letter demands air-gapping and strong sandboxing for cyber-capable AI models.
- Signatories want an international body for standards and containment-failure reporting.
- Demands go beyond Brad Smith’s comments and the UK Parliament’s AI security review.
Full article272 words · extracted from csoonline.com · click to collapse
Current security procedures for training AI models are inadequate, hundreds of AI researchers have warned governments and the AI community. They are calling for tougher rules and the establishment of a new international body overseeing best practice for AI development.
In an open letter the AI specialists — 487, at time of publication, including many senior academics — called for more AI safety research and greater emphasis on containment technologies.
“Strong sandboxing mechanisms including air-gapping (disconnecting from the internet) should be used to provide high-assurance containment of cyber-capable AI models,” say the signatories, who include such luminaries as Geoffrey Hinton and Yoshua Bengio.
The experts said that a new international body, to be set up in consultation with governments and a wide range of AI and security specialists, could set new safety standards but also act as an organization to which containment failures could be reported, improving transparency for learning and accountability purposes.
The scientists’ demands go further than some recent calls for greater regulation of AI. Earlier this week, Microsoft president Brad Smith said AI is less regulated than washing machines or milk, although he made no firm proposals to rectify the situation. And the UK parliament is looking at ways to improve AI security, although any moves will be hampered by disagreement among AI businesses.
Hinton and Bengio are no strangers to this kind of scientist-led initiative. In October last year, they signed an open letter warning of the dangers of developing super-intelligent AI. The letter appears not to have affected AI’s breakneck development; it remains to be seen whether AI players in boardrooms will heed the warning.
Text extracted automatically; images, tables and formatting may be missing. Original: https://www.csoonline.com/article/4236276/cyberattack-ais-must-be-trained-only-on-air-gapped-systems-hundreds-of-ai-researchers-say.html