Ming Ding | Information Security and
Privacy Group | Data61, CSIROPrivacy risk assessment –Examples
•Information uncertainty: 𝐻𝑥|𝑦
➢Intuition: The remaining uncertainty of data (measured by entropy) for a given observation 𝑦
➢This metric quantifies the remaining information of 𝑥notrevealed by observing 𝑦
➢This metric can be evaluated using Information theory or empirical experiments
➢The larger the metric, the stronger the privacy protection
Original data x
(sensitive info: s
non-sensitive info: u)Output/Observation y
(data, query answer, AI/ML
models/parameters, etc.)