Safety
Provable Privacy Attacks on Trained Shallow Neural Networks
arXiv:2410.07632v3 Announce Type: replace Abstract: We study what provable privacy attacks can be shown for trained 2-layer ReLU neural networks, focusing on two types of attacks: membership inference
arXiv:2410.07632v3 Announce Type: replace Abstract: We study what provable privacy attacks can be shown for trained 2-layer ReLU neural networks, focusing on two types of attacks: membership inference and data reconstruction. We prove that theoretical results on the implicit bias of 2-layer neural networks can be used to provably identify with high probability whether a given point was used in the training set in a high-dimensional, nearly orthogonal setting, and can also be used to construct a finite set of which at least a constant fraction are training points in a univariate setting. To the best of our knowledge, our work is the first to show provable vulnerabilities in this implicit-bias-driven setting.
Related
- Impact of Graph Structure on Membership-Inference Risk for Graph Neural Networks
- Causal Evaluation of Membership Inference Attacks
- Membership Inference Attacks for Unseen Classes
- Differential Privacy in Two-Layer Networks: How DP-SGD Harms Fairness and Robustness
Source: arXiv cs.LG | 2026-08-27