ICCV 2025 accepted papers on Federated learning and privacy
40 of the 2,701 papers accepted at ICCV 2025 (1.5%) are on Federated learning and privacy, compared with 1.6% at ICCV 2023. They fall into 4 topics.
See ICCV 2025 in the interactive map
Submitting to ICCV? Checklist →
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 · 23 papers
- LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement (34 citations)
- Federated Continual Instruction Tuning (13 citations)
- Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation (10 citations)
- You Are Your Own Best Teacher: Achieving Centralized-level Performance in Federated Learning under Heterogeneous and Long-tailed Data (9 citations)
- Class-Wise Federated Averaging for Efficient Personalization (6 citations)
- Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learning (5 citations)
- FED-PsyAU: Privacy-Preserving Micro-Expression Recognition via Psychological AU Coordination and Dynamic Facial Motion Modeling (4 citations)
- FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learning (4 citations)
- Personalized Federated Learning under Local Supervision (4 citations)
- FedPall: Prototype-based Adversarial and Collaborative Learning for Federated Learning with Feature Drift (3 citations)
- Tensor-aggregated LoRA in Federated Fine-tuning (3 citations)
- A Framework for Double-Blind Federated Adaptation of Foundation Models (2 citations)
and 11 more in the interactive map.
Privacy attacks and secure learning · 11 papers
- Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning. (5 citations)
- Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning (5 citations)
- Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning (5 citations)
- Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack (5 citations)
- IDFace: Face Template Protection for Efficient and Secure Identification (3 citations)
- Privacy-centric Deep Motion Retargeting for Anonymization of Skeleton-Based Motion Visualization (3 citations)
- Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy (2 citations)
- Boundary Probing for Input Privacy Protection When Using LMM Services
- Sibai: A Few-Shot Meta-Classifier for Poisoning Detection in Federated Learning
- VPR-Cloak: A First Look at Privacy Cloak Against Visual Place Recognition
- Semantic versus Identity: A Divide-and-Conquer Approach towards Adjustable Medical Image De-Identification
Communication-efficient FL · 3 papers
- FedWSQ: Efficient Federated Learning with Weight Standardization and Distribution-Aware Non-Uniform Quantization (5 citations)
- Towards Privacy-preserved Pre-training of Remote Sensing Foundation Models with Federated Mutual-guidance Learning (5 citations)
- EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients (4 citations)
