Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagery

Chang, Ching-Chun and Gao, Kai and Xu, Shuying and Kordoni, Anastasia and Leckie, Christopher and Echizen, Isao (2025) Hypnopaedia-Aware Machine Unlearning via Psychometrics of Artificial Mental Imagery. IEEE Access, 13. pp. 103880-103897. ISSN 2169-3536

Abstract

Neural backdoors represent insidious cybersecurity loopholes that render learning machinery vulnerable to unauthorised manipulations, potentially enabling the weaponisation of artificial intelligence with catastrophic consequences. A backdoor attack involves the clandestine infiltration of a trigger during the learning process, metaphorically analogous to hypnopaedia, where ideas are implanted into a subject’s subconscious mind under the state of hypnosis or unconsciousness. When activated by a sensory stimulus, the trigger evokes a conditioned reflex that directs a machine to mount a predetermined response. In this study, we propose a cybernetic framework for constant surveillance of backdoor threats, driven by the dynamic nature of untrustworthy data sources. We develop a self-aware unlearning mechanism to autonomously detach a machine’s behaviour from the backdoor trigger. Through reverse engineering and statistical inference, we detect deceptive patterns and estimate the likelihood of backdoor infection. We employ model inversion to elicit artificial mental imagery, using stochastic processes to disrupt optimisation pathways and avoid convergent but potentially flawed patterns. This is followed by hypothesis analysis, which estimates the likelihood of each potentially malicious pattern as the true trigger and infers the probability of infection. The primary objective of this study is to maintain a stable state of equilibrium between knowledge fidelity and backdoor vulnerability.