mlsanityData to 7 Oct 2026

Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning

arXiv 2210.10880 ↗First posted 19 Oct 2022cs.LG cs.CRcited by 30

Not on the map. Why?

Abstract (arXiv)

Gradient inversion attack enables recovery of training samples from model gradients in federated learning (FL), and constitutes a serious threat to data privacy. To mitigate this vulnerability, prior work proposed both principled defenses based on differential privacy, as well as heuristic defenses based on gradient compression as countermeasures. These defenses have so far been very effective, in particular those based on gradient compression that allow the model to maintain high accuracy while greatly reducing the effectiveness of attacks. In this work, we argue that such findings underestimate the privacy risk in FL. As a counterexample, we show that existing defenses can be broken by a simple adaptive attack, where a model trained on auxiliary data is able to invert gradients on both vision and language tasks.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 25 of its 34 references that are in the map. First posted on arXiv 19 Oct 2022.

Builds on

25 of 34 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  7. 2016Pointer Sentinel Mixture Modelscited by 2,992
  8. 2016Deep Learning with Differential Privacycited by 2,682
  9. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  10. 2019Deep Leakage from Gradientscited by 1,004
  11. 2018Neural Network Acceptability Judgmentscited by 952
  12. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
13 more
  1. 2018signSGD: Compressed Optimisation for Non-Convex Problemscited by 561
  2. 2019How to Fine-Tune BERT for Text Classification?cited by 409
  3. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  4. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  5. 2017Sparse Communication for Distributed Gradient Descentcited by 243
  6. 2016Practical Secure Aggregation for Federated Learning on User-Held Datacited by 178
  7. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
  8. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 106
  9. 2021Gradient Inversion with Generative Image Priorcited by 101
  10. 2019Deep Set Prediction Networkscited by 71
  11. 2022Recovering Private Text in Federated Learning of Language Modelscited by 67
  12. 2021TAG: Gradient Attack on Transformer-based Language Modelscited by 63
  13. 2022Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Modelscited by 52

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 12; 2025: 11; 2026: 5.

30 papers.

Sort:

By area:

  1. 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 179
  2. 2024AI Risk Management Should Incorporate Both Safety and Securitycited by 17
  3. 2024Model Inversion Attacks: A Survey of Approaches and Countermeasurescited by 11
  4. 2023Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learningcited by 9
  5. 2024Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimationcited by 9
  6. 2025Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attackscited by 9
  7. 2024Analyzing Inference Privacy Risks Through Gradients in Machine Learningcited by 4
  8. 2025From Centralized to Decentralized Federated Learning: Theoretical Insights, Privacy Preservation, and Robustness Challengescited by 4
  9. 2024GI-PIP: Do We Require Impractical Auxiliary Dataset for Gradient Inversion Attacks?cited by 3
  10. 2024Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradientscited by 3
  11. 2024The poison of dimensionalitycited by 3
  12. 2023Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verificationcited by 2
18 more
  1. 2024Dealing Doubt: Unveiling Threat Models in Gradient Inversion Attacks under Federated Learning, A Survey and Taxonomycited by 2
  2. 2024DFDG: Data-Free Dual-Generator Adversarial Distillation for One-Shot Federated Learningcited by 2
  3. 2025Shadow defense against gradient inversion attack in federated learningcited by 2
  4. 2025SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decompositioncited by 2
  5. 2026Mitigating Privacy Risk via Forget Set-Free Unlearningcited by 2
  6. 2025Gradient Inversion Transcript: Leveraging Robust Generative Priors to Reconstruct Training Data from Gradient Leakagecited by 1
  7. 2025Hear No Evil: Detecting Gradient Leakage by Malicious Servers in Federated Learningcited by 1
  8. 2025Detect & Score: Privacy-Preserving Misbehaviour Detection and Contribution Evaluation in Federated Learningcited by 1
  9. 2026How Private Are DNA Embeddings? Inverting Foundation Model Representations of Genomic Sequencescited by 1
  10. 2026No More Guessing: a Verifiable Gradient Inversion Attack in Federated Learningcited by 1
  11. 2024Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspectivecited by 0
  12. 2024Privacy Attack in Federated Learning is Not Easy: An Experimental Studycited by 0
  13. 2025Defending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbationcited by 0
  14. 2025TS-Inverse: A Gradient Inversion Attack Tailored for Federated Time Series Forecasting Modelscited by 0
  15. 2025MAGIA: Sensing Per-Image Signals from Single-Round Averaged Gradients for Label-Inference-Free Gradient Inversioncited by 0
  16. 2025FedVideoMAE: Efficient Federated Video Moderation with Differential Privacy and Secure Aggregationcited by 0
  17. 2026SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacycited by 0
  18. 2026Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learningcited by 0