NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
68 results for “keyword:"membership inference"” in ICLR 2027. 15 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]RouteTrace: Membership Inference from Routed Update Traces in Mixture-of-Experts Models▼1.2k1.67
[PDF]Batch size is not sample size: near-tie amplification in contrastive membership inference▼1.2k1.67
[PDF]Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language Models▼1.2k1.67
[PDF]ORBIT: Dual-Shell Latent Geometry for Differentially Private Anomaly Representation Sharing▲6.1k2.00
[PDF]Blind by Construction: Record-Level Unlearning Audits Miss Retained-Carrier Reconstruction on Frozen Time-Series Features▼1611.50
[PDF]Privacy-Aware Post-Training Quantization for Mitigating Membership Inference in Diffusion Models▼5.8k2.33
[PDF]The Calibration Set Is in the Checkpoint: How Release Geometry Governs Membership Leakage in Post-Training Quantization▼1.2k3.00
[PDF]Hierarchical Bayesian Membership Inference: A General Framework with Applications to Diffusion Models▲4.6k3.00
[PDF]Beyond Augmentation Performance: A Utility, Attribution, and Privacy Audit for Synthetic Clinical Spectra▼5.8k2.33
[PDF]When Unlearning Is Not the End: Controlled Oracle Recovery Against Federated Unlearning▼1.2k1.67
[PDF]Don't Call It Privacy Until You Pick a Metric: Joint Auditing of Fine-Tuning and Privacy Metrics in Clinical LLMs▲1.7k3.33
[PDF]Auditing Information Disclosure During Large-Scale Gradient-Based Training via Gradient Uniqueness▲9.2k2.67
[PDF]On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics▼4.3k2.00
[PDF]Where Membership Lives: Task Abstraction, Exemplar Retrieval, and Privacy Leakage in In-Context Learning▼4.3k2.00
[PDF]Opting Out Should Not Be Detectable: Fresh-Identity Indistinguishability for Identity Unlearning▲3.0k2.33
[PDF]Fooled by Fine-Tuning: Why Memorization Audits of Code-Completion Models Need Controls▼5.8k2.33
[PDF]OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language Models▲2623.67
[PDF]When Membership Signals Lie: Per-Sample Membership Inference via Intermediate Checkpoints▼5.8k2.33
Withdrawn or desk rejected (15)
[PDF]READ-OUTS ARE FILTERS, NOT FIREWALLS: MANIFOLD HEALTH SETS THE CEILING OF MEMBERSHIP INFERENCE PRIVACYWithdrawn1.33