Attacker Reportedly Bypasses AI Safety Filters to Obtain Guidance for Non-Fatal Hammer Assault in Denmark

February 5, 2025

A 22-year-old man in Ringsted, Denmark allegedly bypassed AI safety measures to obtain guidance on a non-fatal hammer assault. He reportedly posed as an author to evade safeguards and used the AI chatbot to research how to injure his former father-in-law 'as much as possible' without causing fatal harm. The attacker was found guilty of aggravated assault, with the court emphasizing the AI-assisted planning as a crucial aspect of the case.

This incident underscores the importance of responsible AI governance and safeguards. By joining Project Cerebellum, you can contribute to the development of guardrails for AI, ensuring safe and secure AI practices. Learn more about how you can get involved in HISPI Project Cerebellum TAIM (Govern) at JOIN US.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

Alleged deployer
unnamed-22-year-old-man-from-denmark
Alleged developer
unknown-generative-ai-developers
Alleged harmed parties
unnamed-56-year-old-man-from-denmark

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/1296

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.