cs.AI, cs.CR, cs.CV, cs.LG

Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagery

arXiv:2410.05284v2 Announce Type: replace-cross
Abstract: Neural backdoors represent insidious cybersecurity loopholes that render learning machinery vulnerable to unauthorised manipulations, potentially enabling the weaponisation of artificial intell…