arXiv Machine Learning
Jun 15
Private Prediction via PAC Privacy
arXiv:2601. 14033v2 Announce Type: replace Abstract: Machine learning models are increasingly served behind APIs.
Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD
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.
Related stories
arXiv Machine Learning
Sep 18
Near-Optimal Machine Unlearning Utility for Smooth Strongly Convex Losses
arXiv:2606. 01527v2 Announce Type: replace 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 Machine Learning
Jun 3
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
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 Machine Learning
Jul 28
DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton
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 Machine Learning
Aug 28
Privacy Without Regret: Differentially Private Inference-Time Alignment
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 Machine Learning
Jul 1
Private Rate-Constrained Optimization with Applications to Fair Learning
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 Machine Learning
Sep 23
Optimizing Canaries for Privacy Auditing with Metagradient Descent
The paper investigates black-box privacy auditing for differentially private learning algorithms, focusing on DP‑SGD. It introduces a method that optimizes the auditor’s canary set using metagradient descent, improving empirical lower bounds on privacy parameters compared to prior canary designs. The approach is shown to be DP‑SGD agnostic and efficient, with optimized canaries for small models remaining effective for larger DP‑SGD models.
arXiv Machine Learning
Jul 23
End-to-End Differential Privacy in Training Deep Neural Network Classifiers
arXiv:2607. 19580v1 Announce Type: new Abstract: Differentially private machine learning enables model training on sensitive data while ensuring that individual data is unlikely to be recoverable from the parameters of the resulting model.
arXiv Machine Learning
Jul 23
Differentially Private Neural Network Training Under the Hidden State Assumption
arXiv:2407. 08233v3 Announce Type: replace Abstract: Current differentially private learning paradigms face a severe utility bottleneck: DP-SGD degrades performance through noise accumulation over training steps, while aggregation-based approaches such as PATE suffer from data inefficiency due to disjoint data partitioning.
arXiv Machine Learning
Jun 5
Minimax optimal differentially private synthetic data for smooth queries
arXiv:2602. 01607v3 Announce Type: replace-cross Abstract: Differentially private synthetic data enables the sharing and analysis of sensitive datasets while providing rigorous privacy guarantees for individual contributors.
arXiv Machine Learning
Sep 1
Revisiting the Provable-Auditable Privacy Gap of DP-SGD
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 AI
4d ago
A Sharp Transition in Data Reconstruction under Differential Privacy
arXiv:2609.37344v1 Announce Type: cross Abstract: Data reconstruction attacks have empirically been successful in recovering training samples from learned models, raising privacy concerns and motivat...