Plaintiff busted trying to use AI prompt injection to win court case, hides text instruction in filing — demands AI model reviewing the text should side with him, rumbled because of strange white spaces in text
A self-represented plaintiff in a Connecticut court added a hidden AI prompt injection attack in their filing in a failed attempt to influence a decision. The court bars them from submitting documents electronically and instead must print them and hand to the clerk of court.
Matthew Elliot, a plaintiff in a court case against the New York Bariatric Group, attempted to use AI prompt injection in two of their filings. Elliot inserted white text using a tiny font size under the heading of their pleading and before the first paragraph, making it invisible to humans but readable by AI models. The hidden instructions were meant to manipulate the AI model reviewing the text to side with Elliot.
However, a court worker noticed the strange white spaces in the text, revealing the hidden instructions. Judge Walter Michael Spader, Jr., issued a show cause order to Elliot to determine whether the conduct violated the rules of practice and duties of good faith in litigation. Elliot claimed their actions were merely an "audit" of the court, but the judge disagreed, stating that the move was an attempt to mislead the Court and other parties.
Brief written by urgent.news from Tom's Hardware's own syndicated text. Machine-written — it may contain errors, so check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
