Foundation Models in Federated Learning: Assessing Backdoor Vulnerabilities
On the map: LLM safety and security → Federated unlearning and poisoning
Abstract (arXiv)
Federated Learning (FL), a privacy-preserving machine learning framework, faces significant data-related challenges. For example, the lack of suitable public datasets leads to ineffective information exchange, especially in heterogeneous environments with uneven data distribution. Foundation Models (FMs) offer a promising solution by generating synthetic datasets that mimic client data distributions, aiding model initialization and knowledge sharing among clients. However, the interaction between FMs and FL introduces new attack vectors that remain largely unexplored. This work therefore assesses the backdoor vulnerabilities exploiting FMs, where attackers exploit safety issues in FMs and poison synthetic datasets to compromise the entire system. Unlike traditional attacks, these new threats are characterized by their one-time, external nature, requiring minimal involvement in FL training. Given these uniqueness, current FL defense strategies provide limited robustness against this novel attack approach. Extensive experiments across image and text domains reveal the high susceptibility of FL to these novel threats, emphasizing the urgent need for enhanced security measures in FL in the era of FMs.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 41 of its 56 references that are in the map. First posted on arXiv 18 Jan 2024.
Builds on
41 of 56 references.
References · 41
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
- 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
- 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
- 2018How To Backdoor Federated Learningcited by 745
- 2022A Survey on In-context Learningcited by 717
29 more
- 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 678
- 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
- 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
- 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
- 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 385
- 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
- 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
- 2022Prompting GPT-3 To Be Reliablecited by 258
- 2019Can You Really Backdoor Federated Learning?cited by 250
- 2019A backdoor attack against LSTM-based text classification systemscited by 214
- 2023On the Adversarial Robustness of Multi-Modal Foundation Modelscited by 142
- 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 141
- 2022PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Modelcited by 133
- 2021Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoningcited by 103
- 2023Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Modelscited by 100
- 2023Backdoor Attacks for In-Context Learning with Language Modelscited by 92
- 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
- 2023When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directionscited by 83
- 2023BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPTcited by 70
- 2023FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learningcited by 59
- 2021A Backdoor Attack against 3D Point Cloud Classifierscited by 50
- 2023An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learningcited by 32
- 2023Towards Personalized Federated Learning via Heterogeneous Model Reassemblycited by 31
- 2021Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filteringcited by 28
- 2023GPT-FL: Generative Pre-trained Model-Assisted Federated Learningcited by 24
- 2022Federated Self-supervised Learning for Video Understandingcited by 13
- 2023Backdoor Threats from Compromised Foundation Models to Federated Learningcited by 8
- 2023Temporal-Distributed Backdoor Attack Against Video Based Action Recognitioncited by 3
- 2023Unveiling Backdoor Risks Brought by Foundation Models in Heterogeneous Federated Learningcited by 3
Built on by
Citing papers per year: 2024: 2; 2025: 1.
3 papers.