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
51 results for “keyword:"protection"” in ICLR 2027. 13 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Do Not Assume Users Are Privacy-Aware: Evaluating Proactive Privacy Risk Warning in Large Language Models▲3972.67
[PDF]Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents▼1.2k1.67
[PDF]Obscrowd: Joint Face-Localized Identity Protection for Multi-Portrait Images under Generative Editing▲3.8k2.50
[PDF]Rethinking Identity Targets for Face De-Identification: Attribute Compatibility Matters▲3972.67
[PDF]CloakFL: Mitigating Global Model Exposure in Federated Learning via Convergence-Aware Proxy Distribution▼13k2.00
[PDF]EMBER: Margin-Targeted Energy Reshaping for Mitigating Exact Memorization in Autoregressive Language Models▼1.2k1.67
[PDF]PRISM: Breaking the Reactive Bottleneck in Retain-Free Unlearning with Proactive Data-Free Structural Priors▼1.2k3.00
[PDF]Hide in Plain Sight: Towards Scalable and Text-only LLM Copyright Auditing via Watermarking Token-wise Attribution▼20k1.67
[PDF]Anamorph: A Secure and Efficient TEE-Shielded Obfuscation Scheme for On-Device LLM Inference▼4.3k2.00
[PDF]SemantiTrace: Stealthy Copyright Tracing in Black-Box Multimodal RAG via Semantic Parasitism▲9.2k2.67
[PDF]PABP: An Approximately Truthful Auction Mechanism for Federated Learning with Bid Privacy Protection▲3972.67
[PDF]PMOPD: Task Ordering, Cycling, and Parameter-Update Subspace Protection in Multi-Teacher On-Policy Distillation▲3972.67
[PDF]Why Subspace Protection Needs a Fixed Rank and Neuron Recycling in Task-Free Continual Learning▲3972.67
[PDF]Key-Recoverable Conditional Flow Hijacking: Authorization-Aware Image Protection for DiT-Based In-Context Editing▲5.4k3.00
[PDF]GSPS: Global Style-guided Protection Synthesis for Ownership Verification and Leakage Tracing of Unlabeled Datasets in Semi-Supervised Learning▼5.8k2.33
Withdrawn or desk rejected (13)
[PDF]What Does a Copyright Budget Certify? An Exact Threshold for Per-Token Meters, and a Length-Independent Certificate for SelectionWithdrawn1.67
[PDF]SOPC: Controllable Privacy-Utility Trade-off via Two-Stage Feature Coding against Model Inversion AttacksWithdrawn
[PDF]RVDGuard: Robust Protection against Unauthorized Image-to-Video Generation via First-Step Velocity DeflectionDesk rejected2.33
[PDF]The Signal Beneath the Words: Paraphrase-Resistant Watermarking for LLM DistillationWithdrawn1.67
[PDF]MidGuard: Frequency-Aware Adversarial Protection for Personalized Diffusion ModelsWithdrawn1.67