If an adversary gives you a machine learning model and secretly plants a malicious backdoor in it, what are the chances that you can discover it? Very little, according to a new paper by researchers at UC Berkeley, MIT, and the Institute of Advanced Study.
Undetectable ML backdoors are a serious concern
Undetectable ML backdoors are a serious…
Undetectable ML backdoors are a serious concern
If an adversary gives you a machine learning model and secretly plants a malicious backdoor in it, what are the chances that you can discover it? Very little, according to a new paper by researchers at UC Berkeley, MIT, and the Institute of Advanced Study.