mlsanityData to 14 Oct 2026

ADI: Adversarial Dominating Inputs in Vertical Federated Learning Systems

arXiv 2201.02775 ↗First posted 8 Jan 2022cs.CR cs.DC cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Vertical federated learning (VFL) system has recently become prominent as a concept to process data distributed across many individual sources without the need to centralize it. Multiple participants collaboratively train models based on their local data in a privacy-aware manner. To date, VFL has become a de facto solution to securely learn a model among organizations, allowing knowledge to be shared without compromising privacy of any individuals. Despite the prosperous development of VFL systems, we find that certain inputs of a participant, named adversarial dominating inputs (ADIs), can dominate the joint inference towards the direction of the adversary's will and force other (victim) participants to make negligible contributions, losing rewards that are usually offered regarding the importance of their contributions in federated learning scenarios. We conduct a systematic study on ADIs by first proving their existence in typical VFL systems. We then propose gradient-based methods to synthesize ADIs of various formats and exploit common VFL systems. We further launch greybox fuzz testing, guided by the saliency score of ``victim'' participants, to perturb adversary-controlled inputs and systematically explore the VFL attack surface in a privacy-preserving manner. We conduct an in-depth study on the influence of critical parameters and settings in synthesizing ADIs. Our study reveals new VFL attack opportunities, promoting the identification of unknown threats before breaches and building more secure VFL systems.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 55 of its 108 references that are in the map. First posted on arXiv 8 Jan 2022.

Builds on

55 of 108 references.

References · 55

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  7. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,516
  8. 2015VQA: Visual Question Answeringcited by 2,506
  9. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  10. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  11. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,214
  12. 2015Teaching Machines to Read and Comprehendcited by 1,049
38 more
  1. 2018Robustness May Be at Odds with Accuracycited by 880
  2. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  3. 2019Towards Federated Learning at Scale: System Designcited by 832
  4. 2016Universal adversarial perturbationscited by 784
  5. 2018How To Backdoor Federated Learningcited by 765
  6. 2018MINE: Mutual Information Neural Estimationcited by 683
  7. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  8. 2017Deep Neural Networks as Gaussian Processescited by 622
  9. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  10. 2018Federated Learning for Mobile Keyboard Predictioncited by 572
  11. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
  12. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  13. 2019Fair Resource Allocation in Federated Learningcited by 394
  14. 2015Adversarial Autoencoderscited by 364
  15. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  16. 2019Robust Aggregation for Federated Learningcited by 317
  17. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 311
  18. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  19. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 300
  20. 2018Distributed learning of deep neural network over multiple agentscited by 279
  21. 2016Hierarchical Question-Image Co-Attention for Visual Question Answeringcited by 278
  22. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  23. 2019Can You Really Backdoor Federated Learning?cited by 255
  24. 2019Simple Black-box Adversarial Attackscited by 251
  25. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 246
  26. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 176
  27. 2019SecureBoost: A Lossless Federated Learning Frameworkcited by 176
  28. 2018Mitigating Sybils in Federated Learning Poisoningcited by 161
  29. 2020Feature Inference Attack on Model Predictions in Vertical Federated Learningcited by 106
  30. 2020Privacy Preserving Vertical Federated Learning for Tree-based Modelscited by 89
  31. 2020Collaborative Machine Learning with Incentive-Aware Model Rewardscited by 71
  32. 2016Simple Black-Box Adversarial Perturbations for Deep Networkscited by 42
  33. 2021A Comprehensive Survey of Incentive Mechanism for Federated Learningcited by 38
  34. 2019Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queriescited by 33
  35. 2021Analysis and Applications of Class-wise Robustness in Adversarial Trainingcited by 33
  36. 2019A Crowdsourcing Framework for On-Device Federated Learningcited by 32
  37. 2020Backdoor attacks and defenses in feature-partitioned collaborative learningcited by 30
  38. 2020Universal Adversarial Perturbations: A Surveycited by 28

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 5; 2026: 1.

9 papers.

  1. 2024Threats and Defenses in Federated Learning Life Cycle: A Comprehensive Survey and Challengescited by 15
  2. 2023VFLAIR: A Research Library and Benchmark for Vertical Federated Learningcited by 8
  3. 2025UniTrans: A Unified Vertical Federated Knowledge Transfer Framework for Enhancing Cross-Hospital Collaborationcited by 5
  4. 2024An Empirical Study on Large Language Models in Accuracy and Robustness under Chinese Industrial Scenarioscited by 3
  5. 2025On the Inference (In-)Security of Vertical Federated Learning: Efficient Auditing against Inference Tampering Attackcited by 0
  6. 2025HASSLE: A Self-Supervised Learning Enhanced Hijacking Attack on Vertical Federated Learningcited by 0
  7. 2025VTarbel: Targeted Label Attack with Minimal Knowledge on Detector-enhanced Vertical Federated Learningcited by 0
  8. 2025VMask: Tunable Label Privacy Protection for Vertical Federated Learning via Layer Maskingcited by 0
  9. 2026Understanding Backdoor Vulnerabilities in Vertical Federated Learning: The Gap Between Research and Practicecited by 0