arXiv:2601. 17360v2 Announce Type: replace-cross Abstract: An adversary observing a model's released prediction can infer sensitive attributes of the queried input, or even reconstruct representatives of the model's training data.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2601. 14033v2 Announce Type: replace Abstract: Machine learning models are increasingly served behind APIs.
arXiv:2607. 16620v1 Announce Type: cross Abstract: Differential privacy (DP) is increasingly deployed to limit membership inference risk in machine-learning systems.
The paper surveys 25 studies that use explainable AI to compromise machine learning models, covering attacks such as model extraction, membership inference, and model inversion. It distinguishes between how explanations are obtained—through target releases, attacker-derived methods, secondary disclosure, privileged access, or global artifacts—and shows that explanations can lower extraction costs and reveal membership signals via statistics, recourse distance, and robustness. The authors compare threat models, signals, and defenses, concluding that no single explanation type is always unsafe and that protection must be tailored to the specific acquisition path and target asset.
arXiv:2606. 00986v1 Announce Type: new Abstract: Federated learning (FL) enables multiple data holders to train machine learning models collaboratively without centralizing raw data, making it useful in privacy sensitive domains such as healthcare and institutional data sharing.
arXiv:2608.28934v1 Announce Type: new Abstract: Differential privacy (DP) has traditionally been used to provide theoretical upper bounds on an algorithm's stability to changing its training data. In...
arXiv:2409. 01062v4 Announce Type: replace Abstract: Model Inversion (MI) attacks pose a significant privacy threat by reconstructing private training data from machine learning models.