arXiv:2606. 01527v1 Announce Type: new Abstract: Machine unlearning is motivated by legal and user-facing requirements to remove the influence of individuals' data from trained models, such as the right to be forgotten.
arXiv:2601. 10237v3 Announce Type: replace Abstract: Differentially Private Stochastic Gradient Descent (DP-SGD) is the dominant paradigm for private training, but its fundamental limitations under worst-case adversarial privacy definitions remain poorly understood.
arXiv:2605. 11170v2 Announce Type: replace Abstract: Noise-based certified machine unlearning currently faces a hard ceiling: the noise magnitude required to certify unlearning typically destroys model utility, particularly for large-scale deletion requests.
arXiv:2607. 23649v1 Announce Type: new Abstract: Differential privacy provides formal privacy guarantees for training neural networks on sensitive data, while Bayesian deep learning offers a principled framework for uncertainty-aware prediction.
arXiv:2412. 09119v3 Announce Type: replace Abstract: Machine unlearning, the process of selectively removing data from trained models, is increasingly crucial for addressing privacy concerns and knowledge gaps post-deployment.
arXiv:2601. 14033v2 Announce Type: replace Abstract: Machine learning models are increasingly served behind APIs.
The paper introduces Private Best-of-N (PrivBoN), a method that adds calibrated Gumbel noise to reward scores during inference-time alignment, achieving both ε-differential privacy and KL-regularized alignment. When the privacy budget exceeds a critical threshold ε*, the noise becomes regret-optimal, matching the theoretical alignment skyline. The authors also propose Private Inference-Time Pessimism (PrivITP), which uses χ^2-regularized rejection sampling and a two-phase Gaussian mechanism to provide ex-post (ε,δ)-DP with a privacy cost independent of the number of responses, and demonstrate that both methods outperform standard Best-of-N across multiple models and datasets.
arXiv:2511. 13999v2 Announce Type: replace Abstract: We study the running time, in terms of first order oracle queries, of differentially private empirical/population risk minimization of Lipschitz convex losses.
arXiv:2606. 02119v1 Announce Type: cross Abstract: Machine unlearning aims to remove the influence of specific forget training data due to privacy, copyright or bias concerns while maintaining the model performance on the remaining retain data.
arXiv:2606. 32005v1 Announce Type: cross Abstract: Stochastic Gradient Descent ($\textsf{SGD}$) is one of the most classical optimization algorithms with favorable theoretical guarantees, yet the practical implementation of $\textsf{SGD}$ differs subtly from its well-known form and is often referred to as Shuffling Stochastic Gradient Descent ($\textsf{Shuffling SGD}$).
arXiv:2505. 22703v2 Announce Type: replace Abstract: Many problems in trustworthy ML can be expressed as constraints on prediction rates across subpopulations, including group fairness constraints (demographic parity, equalized odds, etc.
arXiv:2512. 04008v2 Announce Type: replace Abstract: Training with differential privacy (DP) guarantees dataset members that they cannot be identified by users of the released model.