arXiv Machine Learning
Jun 24
Natural Identifiers for Privacy and Data Audits in Large Language Models
arXiv:2606. 24408v1 Announce Type: new Abstract: Assessing the privacy of large language models (LLMs) presents significant challenges.
Differentially Private Datastore Generation for Retrieval-Augmented Inference
arXiv:2606. 01413v1 Announce Type: cross Abstract: It is crucial for modern on-device AI systems that rely on retrieval-augmented inference to release and share datastores without compromising individual privacy.
Related stories
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.
arXiv Machine Learning
Jun 16
DP-Hype: Federated Differentially Private Hyperparameter Search
arXiv:2510. 04902v3 Announce Type: replace Abstract: Tuning hyperparameters in federated machine learning can substantially impact model performance.
arXiv Machine Learning
Jun 30
Efficient Unlearning with Privacy Guarantees
arXiv:2507. 04771v2 Announce Type: replace-cross Abstract: Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning (ML) models trained on them.
arXiv Machine Learning
Jul 13
LDPKiT: Superimposing Remote Queries for Privacy-Preserving Distillation
arXiv:2405. 16361v4 Announce Type: replace Abstract: To protect privacy in regulated domains such as healthcare and finance, model owners may allow only remote API access while keeping both the training data and model parameters private.
arXiv AI
Jul 22
Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data
arXiv:2606. 16952v2 Announce Type: replace-cross Abstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets.
arXiv Machine Learning
Jun 8
SecretFan: Synthesizing Realistic Data without Breaking Privacy
arXiv:2602. 05833v2 Announce Type: replace Abstract: There is a need for synthetic training and test datasets that replicate statistical distributions of original datasets without compromising their confidentiality.
Hugging Face Trending Papers
Jun 1
IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning
Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity. In practice, many HDP-FL systems employ $\varepsilon$-aware server aggregation to improve model utility by re-weighting client updates according to their declared privacy budgets.
arXiv Machine Learning
Jul 7
GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning
arXiv:2412. 12640v2 Announce Type: replace Abstract: The increasing demand for data privacy, alongside the benefits of aggregating data from networked devices, has catalyzed the emergence of federated learning (FL).
arXiv Machine Learning
Jul 8
Dithered Gaussian Mechanism for Randomness-Efficient Differential Privacy
arXiv:2607. 06320v1 Announce Type: cross Abstract: We present the dithered Gaussian mechanism, a novel alternative to the discrete Gaussian mechanism for differential privacy that discretizes the private output rather than the noise distribution itself.
arXiv AI
Jun 18
Practical Anonymous Two-Party Gradient Boosting Decision Tree
arXiv:2605. 26903v2 Announce Type: replace-cross Abstract: Structured data is well handled by gradient-boosted decision trees (GBDT), which are usually trained on vertically partitioned features across mutually distrustful parties.
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.