{"total":40,"rows":[{"id":"2103.01396","title":"DeepReDuce: ReLU Reduction for Fast Private Inference","created":"2021-03-02","cited_by_count":50,"area":null},{"id":"2202.02340","title":"Selective Network Linearization for Efficient Private Inference","created":"2022-02-04","cited_by_count":31,"area":null},{"id":"2308.10134","title":"AutoReP: Automatic ReLU Replacement for Fast Private Network Inference","created":"2023-08-20","cited_by_count":29,"area":null},{"id":"2309.14331","title":"LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference","created":"2023-09-25","cited_by_count":27,"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":"2301.09254","title":"Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference","created":"2023-01-23","cited_by_count":20,"area":null},{"id":"2106.08475","title":"Circa: Stochastic ReLUs for Private Deep Learning","created":"2021-06-15","cited_by_count":16,"area":null},{"id":"2106.11755","title":"Sphynx: ReLU-Efficient Network Design for Private Inference","created":"2021-06-17","cited_by_count":15,"area":null},{"id":"2407.05633","title":"AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2106.09309","title":"Layer Folding: Neural Network Depth Reduction using Activation Linearization","created":"2021-06-17","cited_by_count":14,"area":null},{"id":"2107.12342","title":"Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning","created":"2021-07-26","cited_by_count":14,"area":null},{"id":"2201.06699","title":"AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inference","created":"2022-01-18","cited_by_count":14,"area":null},{"id":"2302.02292","title":"RRNet: Towards ReLU-Reduced Neural Network for Two-party Computation Based Private Inference","created":"2023-02-05","cited_by_count":12,"area":null},{"id":"2209.11904","title":"CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inference","created":"2022-09-24","cited_by_count":10,"area":null},{"id":"2210.15614","title":"Private and Reliable Neural Network Inference","created":"2022-10-27","cited_by_count":7,"area":null},{"id":"2206.12100","title":"zPROBE: Zero Peek Robustness Checks for Federated Learning","created":"2022-06-24","cited_by_count":6,"area":null},{"id":"2408.03561","title":"MPC-Minimized Secure LLM Inference","created":"2024-08-07","cited_by_count":6,"area":null},{"id":"2304.14836","title":"Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryption","created":"2023-04-26","cited_by_count":5,"area":null},{"id":"2208.13032","title":"RL-DistPrivacy: Privacy-Aware Distributed Deep Inference for low latency IoT systems","created":"2022-08-27","cited_by_count":4,"area":null},{"id":"2304.13274","title":"Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference","created":"2023-04-26","cited_by_count":4,"area":null},{"id":"2310.04604","title":"PriViT: Vision Transformers for Fast Private Inference","created":"2023-10-06","cited_by_count":4,"area":null},{"id":"2209.00411","title":"Efficient ML Models for Practical Secure Inference","created":"2022-08-26","cited_by_count":2,"area":null},{"id":"2209.09424","title":"PolyMPCNet: Towards ReLU-free Neural Architecture Search in Two-party Computation Based Private Inference","created":"2022-09-20","cited_by_count":2,"area":null},{"id":"2309.02820","title":"Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Tasks","created":"2023-09-06","cited_by_count":2,"area":null},{"id":"2402.03629","title":"Disparate Impact on Group Accuracy of Linearization for Private Inference","created":"2024-02-06","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":"2607.23478","title":"ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour","created":"2026-07-26","cited_by_count":2,"area":null},{"id":"2206.13601","title":"Efficient Deep Learning Using Non-Volatile Memory Technology","created":"2022-06-27","cited_by_count":1,"area":null},{"id":"2304.10442","title":"Securing Neural Networks with Knapsack Optimization","created":"2023-04-20","cited_by_count":1,"area":null},{"id":"2307.04077","title":"Towards Fast and Scalable Private Inference","created":"2023-07-09","cited_by_count":1,"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":"2408.15231","title":"DCT-CryptoNets: Scaling Private Inference in the Frequency Domain","created":"2024-08-27","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":"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":"2402.05521","title":"Linearizing Models for Efficient yet Robust Private Inference","created":"2024-02-08","cited_by_count":0,"area":null},{"id":"2403.08024","title":"xMLP: Revolutionizing Private Inference with Exclusive Square Activation","created":"2024-03-12","cited_by_count":0,"area":null},{"id":"2511.11781","title":"Coordinate Descent for Network Linearization","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2512.17398","title":"DeepShare: Sharing ReLU Across Channels and Layers for Efficient Private Inference","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2607.18342","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","created":"2026-07-20","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}],"next_cursor":null}