Planting Undetectable Backdoors in Machine Learning Models
Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. We show how a malicious learner can plant an undetectable backdoor into a classifier. On the surface, such a backdoored classifier behaves normally, but in reality, the learner maintains a mechanism for changing the classification of any input, with only a slight perturbation. Importantly, without the appropriate "backdoor key", the mechanism is hidden and cannot be detected by any computationally-bounded observer. We demonstrate two frameworks for planting undetectable backdoors, with incomparable guarantees. ... https://arxiv.org/abs/2204.06974
beh, puo' essere fatto anche da un insider ciao, s. On 21/04/22 11:45, Marco Ciurcina wrote:
Given the computational cost and technical expertise required to train machine learning models, users may delegate the task of learning to a service provider. We show how a malicious learner can plant an undetectable backdoor into a classifier. On the surface, such a backdoored classifier behaves normally, but in reality, the learner maintains a mechanism for changing the classification of any input, with only a slight perturbation. Importantly, without the appropriate "backdoor key", the mechanism is hidden and cannot be detected by any computationally-bounded observer. We demonstrate two frameworks for planting undetectable backdoors, with incomparable guarantees. ...
https://arxiv.org/abs/2204.06974
_______________________________________________ nexa mailing list nexa@server-nexa.polito.it https://server-nexa.polito.it/cgi-bin/mailman/listinfo/nexa
participants (2)
-
Marco Ciurcina -
Stefano Quintarelli