Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Psychometrics for Hypnopaedia-Aware Machinery via Chaotic Projection of Artificial Mental Imagery

Ching-Chun Chang, Kai Gao, Shuying Xu, Anastasia Kordoni, Christopher Leckie, Isao Echizen

TL;DR

This study proposes a cybernetic framework for constant surveillance of backdoors threats, driven by the dynamic nature of untrustworthy data sources and develops a self-aware unlearning mechanism to autonomously detach a machine's behaviour from the backdoor trigger.

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 conditioned reflex that directs a machine to mount a predetermined response. In this study, we propose a cybernetic framework for constant surveillance of backdoors 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 being 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.

Psychometrics for Hypnopaedia-Aware Machinery via Chaotic Projection of Artificial Mental Imagery

TL;DR

This study proposes a cybernetic framework for constant surveillance of backdoors threats, driven by the dynamic nature of untrustworthy data sources and develops a self-aware unlearning mechanism to autonomously detach a machine's behaviour from the backdoor trigger.

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 conditioned reflex that directs a machine to mount a predetermined response. In this study, we propose a cybernetic framework for constant surveillance of backdoors 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 being 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.
Paper Structure (24 sections, 15 equations, 10 figures, 4 tables, 3 algorithms)

This paper contains 24 sections, 15 equations, 10 figures, 4 tables, 3 algorithms.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. Backdoor Attacks
  4. Backdoor Defences
  5. Problem Statement
  6. Reverse Engineering
  7. Conceptual Framework
  8. Hypnopaedia
  9. Cybernetics
  10. Metacognition
  11. Motivated Forgetting
  12. Memory Retrieval
  13. Butterfly Effect
  14. Psychometrics
  15. Methodology
  16. ...and 9 more sections

Figures (10)

  • Figure 1: Cybernetic framework that consists of learner, controller and unlearner for backdoor awareness.
  • Figure 2: Psychometric profile that shows probability of infection, backdoor trigger, backdoor response and auxiliary forensic information.
  • Figure 3: Illustration of backdoor attack through implanting triggers into samples during the learning phase.
  • Figure 4: Systematic pipeline for backdoor defence consisting of model inversion, hypothesis analysis and machine unlearning.
  • Figure 5: Illustration of multi-scale model inversion for projecting an artificial mental image with a random initial noise.
  • ...and 5 more figures