adversarial robustness 1information dependency 1model inversion attacks 1non-robust features 1privacy 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.LG2026
Reducing information dependency does not cause training data privacy. Adversarially non-robust features do
Rasmus Torp, Shailen K. Smith, Adam Breuer
The paper shows that training data privacy against model inversion attacks is not due to memorization but to the presence of non‑robust adversarial features, and introduces a train…
cs.CV2024
Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures
Sayanton V. Dibbo, Adam Breuer, Juston Moore +1
Recent model inversion attack algorithms permit adversaries to reconstruct a neural network's private and potentially sensitive training data by repeatedly querying the network. In…