privacy-preserving_computation.md

C6. Privacy-Preserving Computation

• [2025/02] A New PPML Paradigm for Quantized Models
• [2025/02] Generating Privacy-Preserving Personalized Advice with Zero-Knowledge Proofs and LLMs
• [2025/02] PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning
• [2025/02] Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense
• [2025/02] SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models
• [2025/02] Encrypted Large Model Inference: The Equivariant Encryption Paradigm
• [2025/01] Scaling Laws for Differentially Private Language Models
• [2025/01] Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography
• [2025/01] MPCache: MPC-Friendly KV Cache Eviction for Efficient Private Large Language Model Inference
• [2025/01] Practical Secure Inference Algorithm for Fine-tuned Large Language Model Based on Fully Homomorphic Encryption
• [2024/12] RAG with Differential Privacy
• [2024/12] DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately
• [2024/12] Large Language Model Federated Learning with Blockchain and Unlearning for Cross-Organizational Collaboration
• [2024/12] RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service
• [2024/12] Federated In-Context LLM Agent Learning
• [2024/12] Privacy-Preserving Large Language Models: Mechanisms, Applications, and Future Directions
• [2024/12] Privacy-Preserving Retrieval Augmented Generation with Differential Privacy
• [2024/12] TruncFormer: Private LLM Inference Using Only Truncations
• [2024/11] Preempting Text Sanitization Utility in Resource-Constrained Privacy-Preserving LLM Interactions
• [2024/11] OML: Open, Monetizable, and Loyal AI
• [2024/11] PipeLLM: Fast and Confidential Large Language Model Services with Speculative Pipelined Encryption
• [2024/11] A Practical and Privacy-Preserving Framework for Real-World Large Language Model Services
• [2024/10] SVIP: Towards Verifiable Inference of Open-source Large Language Models
• [2024/10] LanFL: Differentially Private Federated Learning with Large Language Models using Synthetic Samples
• [2024/10] PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles
• [2024/10] FedSpaLLM: Federated Pruning of Large Language Models
• [2024/10] AERO: Softmax-Only LLMs for Efficient Private Inference
• [2024/10] FRAG: Toward Federated Vector Database Management for Collaborative and Secure Retrieval-Augmented Generation
• [2024/10] Rescriber: Smaller-LLM-Powered User-Led Data Minimization for Navigating Privacy Trade-offs in LLM-Based Conversational Agent
• [2024/10] Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
• [2024/10] Reconstruction of Differentially Private Text Sanitization via Large Language Models
• [2024/10] Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
• [2024/10] Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation
• [2024/10] Adaptively Private Next-Token Prediction of Large Language Models
• [2024/10] Encryption-Friendly LLM Architecture
• [2024/10] PrivTuner with Homomorphic Encryption and LoRA: A P3EFT Scheme for Privacy-Preserving Parameter-Efficient Fine-Tuning of AI Foundation Models
• [2024/09] Secure Multiparty Generative AI
• [2024/09] Confidential Prompting: Protecting User Prompts from Cloud LLM Providers
• [2024/08] Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation
• [2024/08] SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC
• [2024/08] Towards Privacy-Aware Sign Language Translation at Scale
• [2024/08] Casper: Prompt Sanitization for Protecting User Privacy in Web-Based Large Language Models
• [2024/08] MPC-Minimized Secure LLM Inference
• [2024/07] Fine-Tuning Large Language Models with User-Level Differential Privacy
• [2024/07] IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization
• [2024/07] ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets
• [2024/06] Safely Learning with Private Data: A Federated Learning Framework for Large Language Model
• [2024/06] Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning
• [2024/06] The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in Prompts
• [2024/06] Promoting Data and Model Privacy in Federated Learning through Quantized LoRA
• [2024/06] MemDPT: Differential Privacy for Memory Efficient Language Models
• [2024/06] Efficient Differentially Private Fine-Tuning of Diffusion Models
• [2024/06] PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
• [2024/06] Differentially Private Fine-Tuning of Diffusion Models
• [2024/06] PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration
• [2024/05] No Free Lunch Theorem for Privacy-Preserving LLM Inference
• [2024/05] PermLLM: Private Inference of Large Language Models within 3 Seconds under WAN
• [2024/05] LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
• [2024/05] Delving into Differentially Private Transformer
• [2024/05] Locally Differentially Private In-Context Learning
• [2024/04] zkLLM: Zero Knowledge Proofs for Large Language Models
• [2024/03] Efficient Language Model Architectures for Differentially Private Federated Learning
• [2024/03] A Framework for Cost-Effective and Self-Adaptive LLM Shaking and Recovery Mechanism
• [2024/03] DP-TabICL: In-Context Learning with Differentially Private Tabular Data
• [2024/03] Privacy-Preserving Diffusion Model Using Homomorphic Encryption
• [2024/02] LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification
• [2024/02] Privacy-Preserving Language Model Inference with Instance Obfuscation
• [2024/02] PromptCrypt: Prompt Encryption for Secure Communication with Large Language Models
• [2023/10] BumbleBee: Secure Two-party Inference Framework for Large Transformers
• [2023/10] Locally Differentially Private Document Generation Using Zero Shot Prompting
• [2023/09] Differentially Private Synthetic Data via Foundation Model APIs 1: Images
• [2023/09] DP-OPT: Make Large Language Model Your Differentially-Private Prompt Engineer
• [2023/09] Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting
• [2023/09] Improving LoRA in Privacy-preserving Federated Learning
• [2023/09] Privacy-Preserving In-Context Learning for Large Language Models
• [2023/09] Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
• [2023/09] Privately Aligning Language Models with Reinforcement Learning
• [2023/09] DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass
• [2023/08] SIGMA: Secure GPT Inference with Function Secret Sharing
• [2023/07] CipherGPT: Secure Two-Party GPT Inference
• [2023/05] Privacy-Preserving Prompt Tuning for Large Language Model Services
• [2023/05] Privacy-Preserving Recommender Systems with Synthetic Query Generation using Differentially Private Large Language Models
• [2022/10] EW-Tune: A Framework for Privately Fine-Tuning Large Language Models with Differential Privacy