Deduplication-while-Training: A Resilient Paradigm for Privacy-Preserving Cross-Client Deduplication in Federated Learning
cs.CR, cs.DC
Submitted: 2026-09-25
Updated: 2026-09-25
Terminology
Sources
- Earn While You Reveal: Private Set Intersection that Rewards Participants
- SemDeDup: Data-efficient learning at web-scale through semantic deduplication
- DeepSeek-V3 Technical Report
- Federated Learning for Mobile Keyboard Prediction
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- GPT-4 Technical Report
- Carbon Emissions and Large Neural Network Training
- Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
- Pivot: Proactive and Verifiable Threshold Oblivious Pseudorandom Functions From Isogeny Group Actions
- Subject Membership Inference Attacks in Federated Learning
- Llama 2: Open Foundation and Fine-Tuned Chat Models
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs