{"total":19,"rows":[{"id":"2403.10045","title":"Towards Adversarially Robust Dataset Distillation by Curvature Regularization","created":"2024-03-15","cited_by_count":17,"area":null},{"id":"2602.16340","title":"The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks","created":"2026-02-18","cited_by_count":11,"area":null},{"id":"2412.08544","title":"Training Data Reconstruction: Privacy due to Uncertainty?","created":"2024-12-11","cited_by_count":4,"area":null},{"id":"2506.15553","title":"Approximating Language Model Training Data from Weights","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2509.22214","title":"A Law of Data Reconstruction for Random Features (and Beyond)","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2510.07452","title":"PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2312.04590","title":"Reconciling AI Performance and Data Reconstruction Resilience for Medical Imaging","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2509.21296","title":"No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2602.08723","title":"Data Reconstruction: Identifiability and Optimization with Sample Splitting","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2406.02600","title":"Data Quality in Edge Machine Learning: A State-of-the-Art Survey","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2411.06916","title":"Slowing Down Forgetting in Continual Learning","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2411.16458","title":"On the Reconstruction of Training Data from Group Invariant Networks","created":"2024-11-25","cited_by_count":0,"area":null},{"id":"2505.14323","title":"Securing Transfer-Learned Networks with Reverse Homomorphic Encryption","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2505.19019","title":"Querying Kernel Methods Suffices for Reconstructing their Training Data","created":"2025-05-25","cited_by_count":0,"area":null},{"id":"2507.18372","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2605.06519","title":"Efficient Techniques for Data Reconstruction, with Finite-Width Recovery Guarantees","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.17995","title":"Differential Privacy of Gaussian Process Posterior Sampling","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2609.37344","title":"A Sharp Transition in Data Reconstruction under Differential Privacy","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.19743","title":"Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}