{"total":69,"rows":[{"id":"2305.05920","title":"Fast Distributed Inference Serving for Large Language Models","created":"2023-05-10","cited_by_count":145,"area":"inference"},{"id":"2302.04870","title":"Offsite-Tuning: Transfer Learning without Full Model","created":"2023-02-09","cited_by_count":78,"area":null},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2311.04044","title":"PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models","created":"2023-11-07","cited_by_count":37,"area":null},{"id":"2406.01394","title":"PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration","created":"2024-06-03","cited_by_count":28,"area":null},{"id":"2305.02538","title":"Cuttlefish: Low-Rank Model Training without All the Tuning","created":"2023-05-04","cited_by_count":25,"area":null},{"id":"2311.17431","title":"Grounding Foundation Models through Federated Transfer Learning: A General Framework","created":"2023-11-29","cited_by_count":24,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2305.18396","title":"LLMs Can Understand Encrypted Prompt: Towards Privacy-Computing Friendly Transformers","created":"2023-05-28","cited_by_count":22,"area":null},{"id":"2211.13955","title":"MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention","created":"2022-11-25","cited_by_count":20,"area":null},{"id":"2410.02486","title":"Encryption-Friendly LLM Architecture","created":"2024-10-03","cited_by_count":17,"area":null},{"id":"2411.15707","title":"Nimbus: Secure and Efficient Two-Party Inference for Transformers","created":"2024-11-24","cited_by_count":16,"area":null},{"id":"2405.20681","title":"No Free Lunch Theorem for Privacy-Preserving LLM Inference","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2301.02654","title":"Does compressing activations help model parallel training?","created":"2023-01-06","cited_by_count":12,"area":null},{"id":"2411.05818","title":"Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives","created":"2024-11-02","cited_by_count":12,"area":null},{"id":"2502.16782","title":"CipherPrune: Efficient and Scalable Private Transformer Inference","created":"2025-02-24","cited_by_count":10,"area":null},{"id":"2305.15769","title":"MERGE: Fast Private Text Generation","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2308.09923","title":"East: Efficient and Accurate Secure Transformer Framework for Inference","created":"2023-08-19","cited_by_count":9,"area":null},{"id":"2401.00793","title":"SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC","created":"2024-01-01","cited_by_count":9,"area":null},{"id":"2405.05525","title":"Ditto: Quantization-aware Secure Inference of Transformers upon MPC","created":"2024-05-09","cited_by_count":8,"area":null},{"id":"2405.14569","title":"PrivCirNet: Efficient Private Inference via Block Circulant Transformation","created":"2024-05-23","cited_by_count":7,"area":null},{"id":"2405.17485","title":"Comet: A Communication-efficient and Performant Approximation for Private Transformer Inference","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2502.00840","title":"Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2408.03561","title":"MPC-Minimized Secure LLM Inference","created":"2024-08-07","cited_by_count":6,"area":null},{"id":"2412.10652","title":"CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference","created":"2024-12-14","cited_by_count":6,"area":null},{"id":"2506.17336","title":"PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases","created":"2025-06-19","cited_by_count":6,"area":"lr"},{"id":"2605.09104","title":"Token Economics for LLM Agents: A Dual-View Study from Computing and Economics","created":"2026-05-09","cited_by_count":6,"area":"agents"},{"id":"2310.04604","title":"PriViT: Vision Transformers for Fast Private Inference","created":"2023-10-06","cited_by_count":4,"area":null},{"id":"2310.10349","title":"Optimized Layerwise Approximation for Efficient Private Inference on Fully Homomorphic Encryption","created":"2023-10-16","cited_by_count":4,"area":null},{"id":"2407.02960","title":"ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets","created":"2024-07-03","cited_by_count":4,"area":null},{"id":"2505.07239","title":"Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity","created":"2025-05-12","cited_by_count":4,"area":null},{"id":"2409.05414","title":"CipherDM: Secure Three-Party Inference for Diffusion Model Sampling","created":"2024-09-09","cited_by_count":3,"area":"diffusion"},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2309.04875","title":"Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inference","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2410.05331","title":"Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion","created":"2024-10-06","cited_by_count":2,"area":null},{"id":"2412.01042","title":"TruncFormer: Private LLM Inference Using Only Truncations","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2505.10315","title":"Private Transformer Inference in MLaaS: A Survey","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2505.15252","title":"An Efficient Private GPT Never Autoregressively Decodes","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2509.09424","title":"ENSI: Efficient Non-Interactive Secure Inference for Large Language Models","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2603.01499","title":"Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2605.04901","title":"On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference","created":"2026-05-06","cited_by_count":2,"area":null},{"id":"2309.04664","title":"Compact: Approximating Complex Activation Functions for Secure Computation","created":"2023-09-09","cited_by_count":1,"area":null},{"id":"2310.02373","title":"SelectFormer: Private and Practical Data Selection for Transformers","created":"2023-10-03","cited_by_count":1,"area":null},{"id":"2403.07283","title":"A Framework for Cost-Effective and Self-Adaptive LLM Shaking and Recovery Mechanism","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2409.19134","title":"Confidential Prompting: Privacy-preserving LLM Inference on Cloud","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2410.09531","title":"PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimization","created":"2024-10-12","cited_by_count":1,"area":null},{"id":"2502.01289","title":"A Framework for Double-Blind Federated Adaptation of Foundation Models","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2506.02965","title":"PC-MoE: Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMs","created":"2025-06-03","cited_by_count":1,"area":"moe"},{"id":"2506.15307","title":"SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2507.05228","title":"Cascade: Token-Sharded Private LLM Inference","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2602.01621","title":"CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.14778","title":"P$^2$RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-$k$ Retrieval","created":"2026-03-16","cited_by_count":1,"area":"rag"},{"id":"2604.15499","title":"SecureRouter: Encrypted Routing for Efficient Secure Inference","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2604.15728","title":"Privacy-Preserving LLMs Routing","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2607.13093","title":"Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models","created":"2026-07-14","cited_by_count":1,"area":"inference"},{"id":"2312.15229","title":"Regularized PolyKervNets: Optimizing Expressiveness and Efficiency for Private Inference in Deep Neural Networks","created":"2023-12-23","cited_by_count":0,"area":null},{"id":"2402.02320","title":"Spin: An Efficient Secure Computation Framework with GPU Acceleration","created":"2024-02-04","cited_by_count":0,"area":null},{"id":"2407.18982","title":"Low-Latency Privacy-Preserving Deep Learning Design via Secure MPC","created":"2024-07-24","cited_by_count":0,"area":null},{"id":"2409.19120","title":"Secure Multiparty Generative AI","created":"2024-09-27","cited_by_count":0,"area":null},{"id":"2509.24624","title":"PRIVMARK: Private Large Language Models Watermarking with MPC","created":"2025-09-29","cited_by_count":0,"area":"safety"},{"id":"2510.07457","title":"Comparison of Fully Homomorphic Encryption and Garbled Circuit Techniques in Privacy-Preserving Machine Learning Inference","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2602.17223","title":"Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMs","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2602.18758","title":"UFO: Unlocking Ultra-Efficient Quantized Private Inference with Protocol and Algorithm Co-Optimization","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2605.08343","title":"Private Vertical Federated Inference for Time-Series","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2609.01730","title":"HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.23193","title":"LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.35882","title":"GenomeOcean Anywhere: Private WebGPU Inference for Genome MoEs","created":"2026-09-27","cited_by_count":0,"area":"moe"},{"id":"2609.35883","title":"CipherGenome: Homomorphic Inference for Genomic Mixture-of-Experts","created":"2026-09-27","cited_by_count":0,"area":"moe"},{"id":"2610.19607","title":"A Graph-Based Analysis of Comparability, Scale, and Attribution in Private Transformer Inference","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}