Gradient Inversion Attacks

Ask about this topic

Overview

Gradient inversion attacks study how much private data can be recovered from gradients or updates exposed in federated and split learning, including images, text, tabular records, and sequential data. Methods range from matching gradients or intermediate activations to algebraic and sparse recovery, transformer-subspace analysis, and models of multi-step training trajectories. Evaluations use image-classification benchmarks, language models and tokenizers, tabular datasets, and varied batch sizes, architectures, and training protocols. A central tension is that controlled attacks can recover substantial information, while some evaluations find realistic, optimized vision pipelines harder to invert; privacy therefore depends on the model, aggregation, and exposure setting, and defenses must balance leakage reduction with training utility.

Latest papers

CardsList

20 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document

    Oct 2, 2026Georgios Politis, Evangelos PappasPrivacy Leakage in Language ModelsGradient Inversion Attacks

  2. A Path Integral Surrogate for Multi-Step Gradient Inversion in Federated Learning

    Oct 2, 2026Agnivo Ghosh, Saumik BhattacharyaNumerical IntegrationGradient Inversion Attacks

    Department of Electronics and Electrical Communication Engineering Indian Institute of Technology Kharagpur, India

  3. Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning

    Sep 24, 2026Sudip Bhujel, Shanghao Shi, Ruiquan Huang +2Gradient Inversion AttacksTrajectory Reconstruction

    Department of Computer Science, University of Kentucky · Department of Computer Science and Engineering, Washington University in St. Louis

  4. Cascading Gradient Inversion via LT-Code Inspired Peeling in Federated Learning

    Sep 9, 2026Saeed Shariati, Mohsen Alambardar MeybodiGradient Inversion AttacksFederated Learning

    Department of Applied Mathematics and Computer Science, Faculty of Mathematics and Statistics, University of Isfahan, Isfahan 81746-73441, Iran

  5. Gradient Mirage: Trainable yet Label-Unidentifiable Gradients in Large Language Model Split Learning

    Aug 19, 2026Shiyu Miao, Yunlong Mao, Zirui Huang +5Privacy-Preserving Language ModelsGradient Inversion Attacks

    State Key Laboratory for Novel Software Technology, Nanjing University · College of Computer Science and Software Engineering, Hohai University · School of Mathematics, Nanjing University +1

  6. MineGrad: Gradient Inversion Attacks on LoRA Fine-Tuning

    Aug 2, 2026Hasin Us Sami, Swapneel Sen, Basak GulerGradient Inversion AttacksPrivacy Leakage in Language Models

    University of California, Riverside, CA

  7. BettiSplit: Topology-Guided Privacy-Aware Split Learning Against Feature Inversion and Gradient Leakage

    Jul 27, 2026Akarsh K. Nair, Muhammad Arifur Rahman, David Brown +1Gradient Inversion AttacksSplit Federated Learning

    Department of Computer Science Nottingham Trent University Nottingham, United Kingdom · Information and Computer Science Department SDAIA–KFUPM Joint Research Center for AI Interdisciplinary Research Center for Biosystems and Machines King Fahd University of Petroleum & Minerals Dhahran 31261, Saudi Arabia

  8. DecoyFace: Beyond Obfuscation via Controllable and Imperceptible Identity Misdirection for Privacy-Preserving Face Recognition

    Jul 20, 2026Zhihan Ren, Lijun He, Xinyao Wang +2Gradient Inversion AttacksPrivacy-Preserving ML

    Shaanxi Key Laboratory of Deep Space Exploration Intelligent Information Technology, School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an 710049, China

  9. Privacy Leakage in Federated Learning in Radiology Reports: A Comparative Evaluation of Tokenizer-Driven Privacy Risks

    Jul 15, 2026Santhosh Parampottupadam, Andres Martinez, Dimitrios Bounias +3Gradient Inversion AttacksAdversarial Attacks

    German Cancer Research Center (DKFZ), Division of Medical Image Computing, Heidelberg, Germany · Medical Faculty Heidelberg, Heidelberg University, Heidelberg, Germany · Department of Computer Engineering, Bilkent University, Universiteler 06800 Çankaya/Ankara, Türkiye +1

  10. TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction

    Jul 5, 2026Nikos Athanasiou, Ilya A. Petrov, Angela Yao +7Gradient Inversion AttacksVLM Robustness

    Meta, Zürich, Switzerland · Max Planck Institute for Intelligent Systems, Tübingen, Germany · University of Tübingen, Germany +1

  11. TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization

    Jun 16, 2026William Kalikman, Ivo Petrov, Dimitar I. Dimitrov +1Gradient Inversion AttacksTransformer

    ETH Zürich · INSAIT, Sofia University "St. Kliment Ohridski"

  12. Profiling Privacy Preservation Against Gradient Inversion Attacks in Tabular Federated Learning

    May 31, 2026Ivo Osterberg Nilsson, Maximilian Birr Engvall, Viktor Valadi +1Gradient Inversion AttacksAdversarial Attacks

    Department of Computing, Jönköping University, Jönköping, Sweden · Scaleout Systems, Uppsala, Sweden · Department of Information Systems, University of Haifa, Haifa, Israel

  13. No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learning

    Apr 16, 2026Francesco Diana, Chuan Xu, André Nusser +1Gradient Inversion AttacksAdversarial Attacks

    Université Côte d’Azur, France · Inria, France · CNRS, France +1

  14. FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs

    Apr 7, 2026Syed Irfan Ali Meerza, Feiyi Wang, Jian LiuGradient Inversion AttacksPrivacy Leakage in Language Models

    University of Tennessee, Knoxville, TN, USA · Oak Ridge National Laboratory, Oak Ridge, USA · University of Georgia, Athens, GA, USA

  15. Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization

    Apr 1, 2026Hao Fang, Wenbo Yu, Bin Chen +4Gradient Inversion AttacksFederated Learning

    Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, Guangdong, China · School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen 518055, Guangdong, China · Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China

  16. ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery

    Mar 18, 2026Zirui Gong, Leo Yu Zhang, Yanjun Zhang +4Gradient Inversion AttacksFederated Learning

    Griffith University · Swinburne University of Technology · City University of Macau +1

  17. SOMP: Scalable Gradient Inversion for Large Language Models via Subspace-Guided Orthogonal Matching Pursuit

    Mar 17, 2026Yibo Li, Qiongxiu LiGradient Inversion AttacksPrivacy Leakage in Language Models

    Politecnico di Milano / Italy · Aalborg University

  18. Trajectory-Aware Information Matching for Multi-Step Gradient Inversion in Federated Learning

    Sep 26, 2025Li Xia, Jing Yu, Zheng Liu +3Gradient Inversion AttacksAdversarial Attacks

    Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Beijing, 100081, China

  19. Practical Feasibility of Gradient Inversion Attacks in Federated Learning

    Aug 27, 2025Viktor Valadi, Lucas Beerens, Mattias Åkesson +4Gradient Inversion AttacksAdversarial Attacks

    Scaleout Systems Sweden · Recorded Future Sweden · AI Sweden Sweden +1

  20. GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning

    Dec 17, 2024Rui Zhang, Ka-Ho ChowGradient Inversion AttacksAdversarial Attacks

    HKU Musketeers Foundation Institute of Data Science · The University of Hong Kong · Hong Kong SAR, China +1