mlsanityData to 7 Oct 2026

Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaboration

arXiv 2304.11432 ↗First posted 22 Apr 2023cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Vertical federated learning (VFL) is a cloud-edge collaboration paradigm that enables edge nodes, comprising resource-constrained Internet of Things (IoT) devices, to cooperatively train artificial intelligence (AI) models while retaining their data locally. This paradigm facilitates improved privacy and security for edges and IoT devices, making VFL an essential component of Artificial Intelligence of Things (AIoT) systems. Nevertheless, the partitioned structure of VFL can be exploited by adversaries to inject a backdoor, enabling them to manipulate the VFL predictions. In this paper, we aim to investigate the vulnerability of VFL in the context of binary classification tasks. To this end, we define a threat model for backdoor attacks in VFL and introduce a universal adversarial backdoor (UAB) attack to poison the predictions of VFL. The UAB attack, consisting of universal trigger generation and clean-label backdoor injection, is incorporated during the VFL training at specific iterations. This is achieved by alternately optimizing the universal trigger and model parameters of VFL sub-problems. Our work distinguishes itself from existing studies on designing backdoor attacks for VFL, as those require the knowledge of auxiliary information not accessible within the split VFL architecture. In contrast, our approach does not necessitate any additional data to execute the attack. On the LendingClub and Zhongyuan datasets, our approach surpasses existing state-of-the-art methods, achieving up to 100% backdoor task performance while maintaining the main task performance. Our results in this paper make a major advance to revealing the hidden backdoor risks of VFL, hence paving the way for the future development of secure AIoT.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 26 of its 42 references that are in the map. First posted on arXiv 22 Apr 2023.

Builds on

26 of 42 references.

References · 26

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  5. 2016An overview of gradient descent optimization algorithmscited by 1,021
  6. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,012
  7. 2019Deep Leakage from Gradientscited by 1,004
  8. 2016Universal adversarial perturbationscited by 774
  9. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  10. 2020Backdoor Learning: A Surveycited by 412
  11. 2019Federated Machine Learning: Concept and Applicationscited by 409
  12. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
14 more
  1. 2020FedML: A Research Library and Benchmark for Federated Machine Learningcited by 298
  2. 2019Label-Consistent Backdoor Attackscited by 285
  3. 2020Clean-Label Backdoor Attacks on Video Recognition Modelscited by 162
  4. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  5. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 104
  6. 2021Label Leakage and Protection in Two-party Split Learningcited by 87
  7. 2018Universal Adversarial Trainingcited by 85
  8. 2022Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protectioncited by 80
  9. 2020Data Poisoning Attacks on Federated Machine Learningcited by 58
  10. 2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
  11. 2020Backdoor attacks and defenses in feature-partitioned collaborative learningcited by 30
  12. 2021Privacy-preserving Federated Adversarial Domain Adaption over Feature Groups for Interpretabilitycited by 28
  13. 2021Graph-Fraudster: Adversarial Attacks on Graph Neural Network Based Vertical Federated Learningcited by 17
  14. 2022A Framework for Evaluating Privacy-Utility Trade-off in Vertical Federated Learningcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
  2. 2024A Survey on Contribution Evaluation in Vertical Federated Learningcited by 5
  3. 2025Vertical Federated Learning in Practice: The Good, the Bad, and the Uglycited by 4
  4. 2025Cooperative Decentralized Backdoor Attacks on Vertical Federated Learningcited by 3
  5. 2024Backdoor Attack on Vertical Federated Graph Neural Network Learningcited by 1
  6. 2026Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learningcited by 1