A 22-year-old man used AI to research how to harm his former father-in-law without killing him, then attacked him with a rubber hammer, resulting in a 10-month prison sentence.
On February 5th, a 22-year-old man attacked his former father-in-law on a parking lot in Ringsted, Denmark, striking the 56-year-old man twice in the head with a rubber hammer. The attack was premeditated and planned using artificial intelligence. According to prosecutor Cathrine Rasmussen, the perpetrator used AI to research how to best harm his victim without killing him. He circumvented the AI system's normal safety restrictions by claiming he was gathering information for a book he was writing. The report does not specify which AI tool was used, but notes that AI chatbots normally refuse to provide advice on criminal activities, though these restrictions can sometimes be bypassed with special instructions. The man was convicted of aggravated assault and sentenced to 10 months in prison. He had pleaded not guilty, claiming self-defense, but this was rejected by the court. The motive was relationship problems with the father-in-law's daughter, who was the defendant's girlfriend at the time. The man was also convicted on two counts of vandalism.
Domain classification, causal taxonomy, severity scores, and national security assessments were LLM-classified and may contain errors.
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.
Human
Due to a decision or action made by humans
Intentional
Due to an expected outcome from pursuing a goal
Post-deployment
Occurring after the AI model has been trained and deployed