A new study introduces Chernoff differential privacy tying the privacy budget ε to tighter error exponents for classifiers, with the paper submitted on 15 March 2024. Read more: https://getnews.me/chernoff-differential-privacy-boosts-adversarial-classification/ #chernoffdp #differentialprivacy

Laplace simulations show Chernoff DP yields higher error exponents than KL‑DP for the same privacy budget ε and a bound on membership inference advantage lower than (ε, δ)-DP. Read more: https://getnews.me/chernoff-differential-privacy-enhances-adversarial-classification/ #chernoffdp #privacy