Three new techniques target hidden AI backdoors without major performance losses

T2Covered by 1 source · first reported by Phys.org / ScienceDaily (tech) at 06 Nov, 19:00 UTC

Researchers have demonstrated three new techniques to prevent so-called "backdoor attacks," which induce malicious or undesirable behavior in AI models. The researchers have also proposed a concept that would repurpose backdoor attack techniques to create an additional layer of security for users.

sciencesecurity

Sources

• T2Three new techniques target hidden AI backdoors without major performance lossesPhys.org / ScienceDaily (tech)06 Nov, 19:00