A Psychopathological Approach to Safety Engineering in AI and AGI

  • Vahid BehzadanEmail author
  • Arslan Munir
  • Roman V. Yampolskiy
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11094)


The complexity of dynamics in AI techniques is already approaching that of complex adaptive systems, thus curtailing the feasibility of formal controllability and reachability analysis in the context of AI safety. It follows that the envisioned instances of Artificial General Intelligence (AGI) will also suffer from challenges of complexity. To tackle such issues, we propose the modeling of deleterious behaviors in AI and AGI as psychological disorders, thereby enabling the employment of psychopathological approaches to analysis and control of misbehaviors. Accordingly, we present a discussion on the feasibility of the psychopathological approaches to AI safety, and propose general directions for research on modeling, diagnosis, and treatment of psychological disorders in AGI.


AI safety Psychopathology Mental disorder Diagnosis Treatment Artificial General Intelligence 


  1. 1.
    APA: Diagnostic and statistical manual of mental disorders (DSM-5®). American Psychiatric Association Publishing (2013)Google Scholar
  2. 2.
    Ashrafian, H.: Can artificial intelligences suffer from mental illness? A philosophical matter to consider. Sci. Eng. Ethics 23(2), 403–412 (2017)CrossRefGoogle Scholar
  3. 3.
    Atkinson, D.J.: Emerging cyber-security issues of autonomy and the psychopathology of intelligent machines. In: Foundations of Autonomy and Its (Cyber) Threats: From Individuals to Interdependence: Papers from the 2015 AAAI Spring Symposium, Palo Alto, CA (2015).
  4. 4.
    Butcher, J.N., Hooley, J.M.: APA Handbook of Psychopathology: Psychopathology: Understanding, Assessing, and Treating Adult Mental Disorders, vol. 1. American Psychological Association, Washington, D.C. (2018)CrossRefGoogle Scholar
  5. 5.
    Collins, A., Smith, E.E.: Readings in Cognitive Science: A perspective from Psychology and Artificial Intelligence. Elsevier, New York City (2013)Google Scholar
  6. 6.
    Davis, T.O.: Conceptualizing psychiatric disorders using “Four D’s” of diagnoses. Internet J. Psychiatry 1(1), 1–5 (2009)Google Scholar
  7. 7.
    Dennett, D.C.: Artificial intelligence as philosophy and as psychology. In: Brainstorms: Philosophical Essays on Mind and Psychology, pp. 109–26 (1978)Google Scholar
  8. 8.
    FLI: The Landscape of AI Safety and Beneficence Research: Input for Brainstorming at Beneficial AI 2017. Future of Life Institute (2017)Google Scholar
  9. 9.
    Kelly, J., Gooding, P., Pratt, D., Ainsworth, J., Welford, M., Tarrier, N.: Intelligent real-time therapy: harnessing the power of machine learning to optimise the delivery of momentary cognitive-behavioural interventions. J. Ment. Health 21(4), 404–414 (2012)CrossRefGoogle Scholar
  10. 10.
    Kendler, K.S.: The dappled nature of causes of psychiatric illness: replacing the organic-functional/hardware-software dichotomy with empirically based pluralism. Mol. Psychiatry 17(4), 377 (2012)CrossRefGoogle Scholar
  11. 11.
    Kotseruba, I., Tsotsos, J.K.: A review of 40 years of cognitive architecture research: core cognitive abilities and practical applications. arXiv preprint arXiv:1610.08602 (2016)
  12. 12.
    Montague, P.R., Hyman, S.E., Cohen, J.D.: Computational roles for dopamine in behavioural control. Nature 431(7010), 760 (2004)CrossRefGoogle Scholar
  13. 13.
    Nordström, A.L., et al.: Central D2-dopamine receptor occupancy in relation to antipsychotic drug effects: a double-blind pet study of schizophrenic patients. Biol. Psychiatry 33(4), 227–235 (1993)CrossRefGoogle Scholar
  14. 14.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (1998)Google Scholar
  15. 15.
    Yampolskiy, R.V.: Utility function security in artificially intelligent agents. J. Exp. Theor. Artif. Intell. 26(3), 373–389 (2014)CrossRefGoogle Scholar
  16. 16.
    Yampolskiy, R.V.: Taxonomy of pathways to dangerous artificial intelligence. In: AAAI Workshop: AI, Ethics, and Society (2016)Google Scholar
  17. 17.
    Yampolskiy, R.V.: Detecting qualia in natural and artificial agents. arXiv preprint arXiv:1712.04020 (2017)

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Vahid Behzadan
    • 1
    Email author
  • Arslan Munir
    • 1
  • Roman V. Yampolskiy
    • 2
  1. 1.Kansas State UniversityManhattanUSA
  2. 2.University of LouisvilleLouisvilleUSA

Personalised recommendations