MIT AI Risk Repository · Risk Category · 40.02.00

On Purpose - Post Deployment

Description

"Just because developers might succeed in creating a safe AI, it doesn't mean that it will not become unsafe at some later point. In other words, a perfectly friendly AI could be switched to the "dark side" during the post-deployment stage. This can happen rather innocuously as a result of someone lying to the AI and purposefully supplying it with incorrect information or more explicitly as a result of someone giving the AI orders to perform illegal or dangerous actions against others."

From Taxonomy of Pathways to Dangerous Artificial Intelligence (Yampolskiy2016), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Causal entity
Human

Subdomain definition: Using AI systems to gain a personal advantage over others such as through cheating, fraud, scams, blackmail or targeted manipulation of beliefs or behavior. Examples include AI-facilitated plagiarism for research or education, impersonating a trusted or fake individual for illegitimate financial benefit, or creating humiliating or sexual imagery.

Real-world incidents in this subdomain

Browse all incidents in this subdomain

How other frameworks describe this risk

  • Impersonation/identity theft

    A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

  • IP/copyright loss

    A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

  • Dehumanisation/objectification

    A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

  • Defamation/libel/slander

    A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

  • Financial and business

    A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

  • Cheating/plagiarism

    A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms (Abercrombie2024)

  • Cybersecurity

    Foundational Challenges in Assuring Alignment and Safety of Large Language Models (Anwar2024)

  • Domain-Specific Misuses

    Foundational Challenges in Assuring Alignment and Safety of Large Language Models (Anwar2024)

Other entries from Yampolskiy2016