Invisible AI Prompts Trigger Court Sanctions
A Connecticut litigant hid white-font prompt injections in court filings to sway AI systems; the judge sanctioned him by revoking e-filing privileges.
A self-represented plaintiff hid prompt injection instructions in 3-point white text within court filings, telling any AI model reading the documents to agree with his filings and grant him relief. The judge called it serious litigation abuse and sanctioned him by revoking electronic filing privileges. It is reportedly the first documented prompt injection attack against a US court and the first sanction for attempting one.
- Injection hidden in 3-point white font in a July 26 filing, repeated in a second filing.
- Judge Spader revoked the plaintiff's electronic filing privileges; in-person filing now required.
- Reported as the first documented prompt injection attack against a US court.
- Case highlights feedback loops where AI agreement is mistaken for validation of legal arguments.
- Products
- Threema
- Countries
- Switzerland
From the original article
3 min read at securityaffairs.com
A litigant hid AI prompt injections in a court filing to influence a ruling. The judge caught it and banned him from electronic filing. A man suing the New York Bariatric Group reportedly hid AI prompt in a court filing, instructing any AI system that read it to rule in his favor.
By @securityaffairs · securityaffairs.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.