Homomorphic Encryption

Ask about this topic

Overview

Homomorphic encryption allows a service to process encrypted data without seeing the underlying inputs, then return results that the data owner can decrypt. Research applies schemes such as CKKS for approximate arithmetic and TFHE for Boolean operations to neural-network and Transformer inference, federated learning, retrieval, and sensing. To reduce cost, systems use SIMD packing, polynomial approximations, fewer bootstraps, specialized hardware, and joint design of cryptographic protocols and model architectures. The central challenge is making encrypted computation practical at useful accuracy and scale while controlling latency, memory, communication, and privacy leakage.

Latest papers

CardsList

41 papers3 papers in the last four weeks, down 62% on the four weeks before. 0.0% of all new papers.

  1. Static Bootstrap Placement for Encrypted Language Model Decoding

    Oct 4, 2026Halil Ibrahim Kanpak, Didem UnatPrivacy-Preserving Language ModelsLLM Inference

    Department of Computer Engineering, Koç University, Istanbul, Türkiye

  2. Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints

    Oct 1, 2026Abid Mohamed Nadhir, Ahmad Al Hanbali, Beggas MounirHomomorphic EncryptionPrivacy-Preserving ML

    El Oued University, El Oued, Algeria · King Fahd University of Petroleum and Minerals (KFUPM), Dhahran, Saudi Arabia · Interdisciplinary Research Center For Smart Mobility and Logistics, KFUPM, Dhahran, Saudi Arabia

  3. Fiona: Accelerating FHE Inference with Packing-Aware Ternary Weights

    Sep 28, 2026Yiteng Peng, Zhibo Liu, Dongwei Xiao +1Mixed-Precision QuantizationEfficient Neural Network Inference

    The Hong Kong University of Science and Technology · State Key Laboratory of Novel Software Technology, Nanjing University

  4. CipherGenome: Homomorphic Inference for Genomic Mixture-of-Experts

    Sep 27, 2026Guang Yang, Fengchen LiuMixture-of-Experts InferencePrivacy-Preserving Language Models

    University of California, Los Angeles · University of California, Berkeley

  5. Encryptability As a Coordinate Choice: Depth-One Homomorphic Federated Learning of Quantum Neural Networks

    Sep 24, 2026Marcel Mordarski, Nathan Mani, Arshad Patel +2Quantum Federated LearningPrivacy-Preserving ML

    Department of Computing, Imperial College London London SW7 2AZ, United Kingdom

  6. HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference

    Sep 18, 2026Byeongseo Min, Yongwoo Lee, Young-Sik Kim +1LLM SecurityJailbreak Defense

    Pohang University of Science and Technology (POSTECH) · Inha University · Daegu Gyeongbuk Institute of Science and Technology (DGIST)

  7. OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design

    Sep 15, 2026Jiangrui Yu, Ye Yu, Si Chen +5Efficient Neural Network InferenceSecure Multi-Party Computation

    Peking University, Beijing, China · Open Security Research, Shenzhen, China · Tsinghua University, Beijing, China

  8. EI-DDLGN: Efficient Encrypted Inference with Deep Differentiable Logic Gate Networks under TFHE

    Sep 12, 2026Mahmoud Y. M. Yassin, Mahmoud AbdelHafeez Sayed, Mostafa TahaDifferentiable Logic Gate NetworksPrivacy-Preserving ML

    Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada

  9. Encrypt What Matters: When Selective Homomorphic Inference Is Efficient

    Sep 8, 2026Ali Backour, Juan Reyes, Jaime Punyed +1Efficient InferenceSelective Inference

    Massachusetts Institute of Technology Cambridge, MA 02139

  10. Pushing Forward Multi-Secret-Key Homomorphic Encryption for Private Average Aggregation

    Sep 1, 2026Miguel Morona-Mínguez, Fernando Pérez-González, Alberto Pedrouzo-UlloaFederated Learning AggregationHomomorphic Encryption

    aatlanTTic, Universidade de Vigo, Escola de Enxeñaría de Telecomunicación, Vigo, 36310, Galicia, Spain

  11. HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation

    Sep 1, 2026Alessandro Zirilli, Davide Marincione, Evgenios M. Kornaropoulos +2Privacy-Preserving Language ModelsHomomorphic Encryption

    Sapienza University of Rome · George Mason University · Paradigma

  12. SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoring

    Aug 27, 2026Baran Can Gül, Hanuma Siddhartha Tunuguntla, Anjana Arvind Naik +3Privacy-Preserving Federated LearningDifferentially Private Federated Learning

    Institute of Industrial Automation and Software Engineering, University of Stuttgart, Stuttgart, Germany · EngD Automotive Systems Design, Eindhoven University of Technology (TU/e), Eindhoven, The Netherlands

  13. GoldenRetriever: Non-Interactive Homomorphic Encrypted Retrieval for Privacy-Preserving RAG

    Jul 31, 2026Yang Gao, Gang Quan, Scott Piersall +3Retrieval-Augmented GenerationHomomorphic Encryption

    Department of Computer Science, University of Central Florida, Orlando, FL, USA · Electrical and Computer Engineering Department, Florida International University, Miami, FL, USA · College of Design, Construction and Planning, University of Florida, Gainesville, FL, USA

  14. ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour

    Jul 26, 2026Jianhang Xie, Sicheng Tan, Vishnu Naresh Boddeti +1Efficient Transformer InferenceHomomorphic Encryption

    City University of Hong Kong · Shandong University · Michigan State University

  15. PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption

    Jul 20, 2026Sahaj Majavdia, Mahdi TaheriEfficient Neural Network InferenceHomomorphic Encryption

    Brandenburgische Technische Universität Cottbus-Senftenberg, Germany · Humboldt University of Berlin, Germany · Tallinn University of Technology, Tallinn, Estonia

  16. Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers

    Jul 6, 2026Ligong Han, Kai Xu, Hao Wang +3Efficient Transformer InferenceTransformer Inference

    MBZUAI IFM · Red Hat AI Innovation · MIT-IBM Watson AI Lab +3

  17. Arbitrary Reduction of Validation Error for AI Decision Tests using Homomorphic AI and Repetition Codes

    Jun 27, 2026Eric Filiol, Jaagup SeppHomomorphic EncryptionPrivacy-Preserving ML

    Independent Researcher - Retired Professor · Hope4Sec, Tallinn, Estonia

  18. TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems

    Jun 25, 2026Ngoc Bao Anh Le, Thai T. Vu, John Le +2Efficient Neural Network InferenceHomomorphic Encryption

    University of Wollongong Wollongong, Australia

  19. Homomorphic Encryptions for Privacy Preserving Vision

    Jun 23, 2026Preey Shah, Rohan Virani, Sanjari SrivastavaHomomorphic EncryptionPrivacy-Preserving ML

  20. ComputeFHE: A Privacy-Preserving General-Purpose Computation Library

    Jun 23, 2026Faris Serdar Tasel, Efe CiftciHomomorphic Encryption

    Department of Computer Engineering, Çankaya University, Ankara, Turkey · Computer Programming Program, Çankaya University, Ankara, Turkey

  21. Detecting and Understanding Vulnerabilities in Fully Homomorphic Encryption Frameworks

    Jun 21, 2026Yiteng Peng, Dongwei Xiao, Zhibo Liu +2Automated Software TestingSoftware Vulnerability Detection

    The Hong Kong University of Science and Technology · State Key Laboratory of Novel Software Technology, Nanjing University · Nara Institute of Science and Technology

  22. FEnc2^2: Unifying Data Packing for Efficient Private Inference via Convolution and Architecture-Aware Fragment Encoding

    Jun 15, 2026Ran Ran, Zhaoting Gong, Nuo Xu +3Efficient Neural Network InferenceHomomorphic Encryption

    North Carolina State University · University of Minnesota · University of California, Santa Cruz +1

  23. Preserving Data Privacy in Learning Causal Structure with Fully Homomorphic Encryption

    Jun 3, 2026Jian Yang, Yuan Tong, Qinbin Li +2Causal DiscoveryCausal Structure Learning

    Hong Kong University of Science and Technology (Guangzhou) · Hong Kong University of Science and Technology · University of California, Berkeley

  24. Privacy-Enhanced Zero-Order Federated Learning via xMK-CKKS over Wireless Channels

    May 28, 2026Anthony Ayli, Khalil Harris, Jihad Fahs +1Federated Learning AggregationHomomorphic Encryption

  25. Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms

    May 27, 2026Yvonne Zhou, Mingyu Liang, Ivan Brugere +5Differentially Private Stochastic Gradient DescentHomomorphic Encryption

    University of Maryland, College Park, MD 20742 · J.P. Morgan AI Research, New York, NY, 10017 · AlgoCRYPT CoE

  26. Encrypted Neural Networks without Overflows

    May 21, 2026Philipp Kern, Lorenzo Rovida, Samuel Teuber +3Neural Network VerificationHomomorphic Encryption

    Karlsruhe Institute of Technology, Germany · Polytechnic University of Turin, Italy · The University of Manchester, UK +2

  27. Decision-Aware Quadratic ReLU Replacement for HE-Friendly Inference

    May 21, 2026Rui Li, Wenyuan Wu, Weijie MiaoEfficient Neural Network InferenceHomomorphic Encryption

    Chongqing Key Laboratory of Secure Computing for Biology, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, 266 Fangzheng Avenue, Beibei District, Chongqing 400714, China · Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong, China

  28. Public-Decay Homomorphic State Space Models for Private Sequence Inference

    May 15, 2026Luis BritoEfficient Neural Network InferenceHomomorphic Encryption

    School of Technology and Management (ESTG-IPVC) Polytechnic Institute of Viana do Castelo, Viana do Castelo, Portugal

  29. Privacy-Preserving Federated Learning via Differential Privacy and Homomorphic Encryption for Cardiovascular Disease Risk Modeling

    Apr 30, 2026Gaurang Sharma, Juha Pajula, Aada Illikainen +4Homomorphic EncryptionPrivacy-Preserving ML

    VTT Technical Research Centre of Finland Ltd, 33720, Tampere, Finland · VTT Technical Research Centre of Finland Ltd, 02150, Espoo, Finland · Solita Oy, 00100 Helsinki, Finland +1

  30. Training Machine Learning Models on Encrypted Data: A Privacy-Preserving Framework using Homomorphic Encryption

    Apr 25, 2026Alexandre Marques, Beatriz Sá, Rui Botelho +1Homomorphic EncryptionPrivacy-Preserving ML

    ISEP, School of Engineering, Polytechnic of Porto, Porto, Portugal · GECAD, Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development, Porto, Portugal