The machine giveth and the machine taketh away: a parrot attack on clinical text deidentified with hiding in plain sight

David S. Carrell, David J. Cronkite, Muqun Rachel Li, Steve Nyemba, Bradley A. Malin, John S. Aberdeen, Lynette Hirschman

Abstract: Clinical corpora can be deidentified using a combination of machine-learned automated taggers and hiding in plain sight (HIPS) resynthesis. The latter replaces detected personally identifiable information (PII) with random surrogates, allowing leaked PII to blend in or “hide in plain sight.” We evaluated the extent to which a malicious attacker could expose leaked PII in such a corpus.