Le mythe dangereux qui se cache derrière les piratages d’agents d’IA
Publié
05 octobre 2026
Par
Yoshua Bengio
Catégorie
IA sécuritaire
We now know that leading AI companies are investigating tens of thousands of situations in which agents have undertaken unwanted actions, some of which would be considered crimes if committed by a human.
In the aftermath of the attack on Hugging Face this summer by OpenAI agents and the recent hack of the Australian national healthcare database, a dangerous myth has gained traction: that these incidents are just cyber security problems and that upgrading the security of the sandboxes in which models are trained would prevent future hacks. [...]
- Article précédent Discours du professeur Yoshua Bengio devant le Conseil de sécurité de l’ONU
- Article suivant Bengio : « Si vous privilégiez la sécurité, quittez les entreprises pionnières en IA »