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
35 results for “keyword:"privacy preserving machine learning"” in ICLR 2027. 4 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]RESAD: Round-Efficient Secure Autoregressive Decoding Scheme for Transformer Inference▼4.3k2.00
[PDF]Send the Brain, Keep the Body: Hybrid Private Transformer Inference with Minimal Secret Control▼1601.50
[PDF]Error Propagation-Aware Scale Design for Efficient Homomorphic Encryption-Based LLM Inference▼5.8k2.33
[PDF]CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption▲5.4k3.00
[PDF]Mitigating Privacy Leakage in Text Corpora via Adaptive Masking and Contextual Reconstruction▼4.3k2.00
[PDF]COQUAD: CO-OPTIMIZED QUADRATIC ACTIVATIONS FOR EFFICIENT PRIVATE TRANSFORMER INFERENCE▼4.5k2.67
[PDF]Who Influenced This Behavior? Auditing Federated LLMs Without Revealing Client Updates▼5.8k2.33
[PDF]Duplex: Actively Secure, Dealer-Free Two-Party Function Secret Sharing for Private LLM Inference▼5.8k2.33
[PDF]Efficient Deterministic Truncation and RMFE-Native Fixed-Point Operators for Private Neural Network Training▲6.1k2.00
[PDF]OBELISK: Co-designing Post-Packing Execution for Efficient Transformer Inference under Fully Homomorphic Encryption▼4.5k2.67
[PDF]Metric-Normalized Posterior Leakage (mPL): Attacker-Aligned Privacy for Joint Consumption▼5.8k2.33
[PDF]RACE-HE: Rotation-Aware Compression for Efficient Private Inference with Homomorphic Encryption▼5.8k2.33
[PDF]Jacobian-Guided Anisotropic Noise Reshaping for Enhancing Representation Utility under Local Differential Privacy▼5.8k2.33
[PDF]Encryptability As a Coordinate Choice: Depth-One Homomorphic Federated Learning of Quantum Neural Networks▲11k2.00
Withdrawn or desk rejected (4)
[PDF]Allocate Before You Perturb: Adaptive Shared Release Spaces for Client-Level Differentially Private Federated LearningDesk rejected2.00
[PDF]BOLT: Boolean-feature One-release Label Transfer for Differentially Private Tabular Synthetic DataDesk rejected