2 papers
cs.LG2026
Adaptive Model Inversion Attacks Generalize a Privacy-Robustness Tradeoff
Shailen Smith, Rasmus Torp, Adam Breuer
In this paper, we show that standard evaluations of high-resolution Model Inversion Attacks (MIAs) significantly underestimate training-data privacy leakage. State-of-the-art priva…
cs.LG2026
Reducing information dependency does not cause training data privacy. Adversarially non-robust features do
Rasmus Torp, Shailen K. Smith, Adam Breuer
In this paper, we challenge the prevailing view that information dependency (including rote memorization) drives training data exposure to image reconstruction attacks. We show tha…