Fair fine-tuning under Equalized Odds yields a tight bound Adv(A, M_f) ≤ Δ_EO · W on adversarial advantage in distribution inference attacks, with empirical reductions below detection threshold across six datasets.
Russo Latona, C
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Modeling projects as networks provides more consistent estimates of resilience to key personnel loss than existing methods.
citing papers explorer
-
Fair Finetuning Mitigates Distribution Inference Attacks
Fair fine-tuning under Equalized Odds yields a tight bound Adv(A, M_f) ≤ Δ_EO · W on adversarial advantage in distribution inference attacks, with empirical reductions below detection threshold across six datasets.