ECCV 2026 accepted papers on Federated learning and privacy
24 of the 2,834 papers accepted at ECCV 2026 (0.8%) are on Federated learning and privacy, compared with 0.9% at ECCV 2024. They fall into 4 topics.
See ECCV 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Personalized and heterogeneous FL · 13 papers
- Neural Collapse-Inspired Multi-Label Federated Learning under Label-Distribution Skew (2 citations)
- Capturing Spectral and Spatial Patterns for Federated Remote Sensing Segmentation
- FeDepth: Federated Learning for Depth Estimation under Robot Heterogeneity
- FedMental: Topology-Aware Federated Prototype Learning for Polymorphic Multimodal Psychiatry
- FedNASP: Federated Vision-Language Navigation with Adaptive Step-wise Personalization
- Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning
- Identifiable Gated Residual Personalization for Federated Parameter-Efficient Fine-Tuning
- Prevention over Correction: Learning Aligned Representations in One-shot Federated Learning
- Prototype Normalization: Optimizing Prototype Separation for Heterogeneous Federated Learning
- SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning
- AnaPFL: When Closed-Form Solutions Meet Generalizationand Personalization in Personalized Federated Learning
- Benchmarking Federated Learning & Knowledge Distillation for Point Cloud Classification
and 1 more in the interactive map.
Privacy attacks and secure learning · 6 papers
- Compositional Non-Face Re-Identification Pressure under Cumulative Vision Releases
- Diffusion to Obfuscation: Time-Adaptive Synthesized Generation Against Gradient Leakage Attacks in Federated Learning
- FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs
- One Trap to Block Them All: Defending Encoder Stealing via Isotropic Uniformity
- Proteus: Model Leakage-Induced Adversarial Attack in Federated Learning
- Vulnerability of Privacy-Preserving Visual Localization against Diffusion-based Attacks
Differential privacy · 3 papers
- Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs (2 citations)
- Spectral Gradient Orthogonalization Improves Differentially Private Training at Scale (1 citation)
- COVERT: Privacy-Preserving Covariant Obfuscation for VLMaaS via Exact Reparameterization and Tailored Tuning
