Connecticut Judge Flags First AI-Prompt Injection Attempt in US Court Filing

A Connecticut judge has identified what appears to be the first instance of a US plaintiff hiding AI-readable instructions inside court filings to try to influence the outcome of a case. The hidden text was formatted to be invisible to humans but legible to software, directing any AI reviewing the document to support the plaintiff’s arguments and disregard prior court denials. The judge ruled that the tactic had no impact on the case, as the filing was considered on its merits, but warned that it sets a dangerous precedent as AI tools become more common in the courts.

Get the app vidgetc Tech, gaming & AI news — always at hand Google Play · Soon App Store
Discuss

Comments

Next articleLe Figaro reporting is coming to ChatGPT→
Start typing to search