Sep 2026· IEEE Internet of Things Journal· Vol 13, pp. 38642-38652· 0 citations· 35 references
Abstract
Vertical federated learning (VFL) is a distributed machine learning paradigm designed for scenarios with vertically partitioned data features, making it highly compatible with Internet of Things (IoT) ecosystems. While promoting collaborative modeling among IoT devices, VFL also introduces new security risks, particularly backdoor attacks. Existing VFL backdoor attacks typically establish associations between triggers and target labels during the training phase by manipulating intermediate model outputs, making them easily detectable by advanced defense mechanisms. This article proposes a hijacking-based backdoor attack (HBA), which, for the first time, innovatively achieves a backdoor attack by exchanging the forward embeddings during the VFL prediction phase, without embedding traditional triggers. HBA leverages intrinsic semantic relationships in the embedding space to hijack the decision-making process of the top model during inference. HBA’s effectiveness depends on the discriminative nature of the features extracted by the bottom model, and since it does not alter the training process, it can evade most defense mechanisms based on training behavior monitoring. Experiments demonstrate that HBA achieves an attack success rate of 99.9% in classification tasks without compromising the original task’s accuracy. Furthermore, existing defense mechanisms struggle to effectively counter HBA without degrading the model’s original task performance.
The rapid adoption of Internet of Things (IoT) devices has accelerated the need for privacy-preserving machine learning techniques, such as federated learning (FL). However, the decentralized and collaborative nature of FL makes it vulnerable to backdoor attacks, where adversaries locally update their malicious models before contributing to the global aggregation, subtly injecting backdoors without degrading the normal performance. An affected model behaves as expected during regular operations but exhibits malicious behavior when an embedded trigger is presented. In this article, we propose a novel self-supervised contrastive-learning-based approach to detect and mitigate backdoor attacks in FL within IoT environments. Unlike conventional reverse-engineering methods that iterate through each class in the dataset to reconstruct triggers, our approach directly regenerates triggers from compromised global models without class iteration. This is achieved by comparing last-layer feature representations of a potentially compromised model with those of a relatively clean model under the guidance of contrastive loss. The reverse-engineered trigger is then leveraged to patch the global model and remove the backdoors. We evaluate our method on three benchmark datasets under two federated backdoor attack scenarios, simulating IoT device collaborations. Extended experiments are also conducted on a transformer-based model and two mitigation methods to assess the robustness of our approach. Our results demonstrate that while traditional reverse-engineering techniques are effective in centralized settings, they struggle to detect backdoors in FL. Comparatively, our method is resilient against backdoor attacks across various settings. In addition, our method is more time-efficient because of its capability of generating the backdoor trigger directly without iterating through all classes.
Hal Ferguson, Rui Ning, Hongyi Wu et al.· IEEE Internet of Things Jour...· 0 citations
This work employs the novel dimensionality reduction technique UMAP and a stringent filtering mechanism to effectively identify and exclude potential malicious participants without relying on traditional noise addition methods and demonstrates that the proposed method maintains high main task accuracy while effectively mitigating backdoor attacks across various attack scenarios.
This work proposes CAEBA (Conditional AutoEncoder Backdoor Attack), a dynamic hidden backdoor framework that uses a conditional autoencoder to generate target-aware and visually stealthy triggers while progressively implanting the backdoor through federated optimization.
Vertical Federated Learning (VFL) allows multiple organizations with disjoint feature spaces and overlapping sample identities to collaboratively train machine learning models while keeping local data. Despite its privacy-preserving design, recent studies have shown that VFL is vulnerable to backdoor attacks. In particular, a malicious passive party can inject a carefully crafted trigger into its local inputs or intermediate embeddings, causing the global model to produce targeted mispredictions at inference time. Existing backdoor attacks in VFL (e.g., BadVFL) rely on the assumption that the malicious client can obtain additional knowledge about task labels, which contradicts the core privacy assumptions of VFL. In this paper, we propose GOFA, a new backdoor attack method for VFL scenarios. GOFA uses the gradient feedback from the server to construct a poisoned dataset and employs an adversarial example attack (e.g., FGSM) for masking the original features of the data to enhance trigger learning. We use the CIFAR-10 and UCI-HAR datasets. Our experiments demonstrate the effectiveness of our method in various settings.
Ye Cheng, Naotoshi Adachi· 2026 6th International Confe...· 0 citations
Federated learning (FL) has been widely applied in Internet of Things (IoT) systems. However, its inherently distributed nature makes it vulnerable to backdoor attacks. Existing attacks typically design triggers based on fixed patterns or local models, without considering their applicability to the global model. Consequently, a significant “loss” occurs during the transfer of the backdoor from the local model to the global model, leading to a low Attack Success Rate (ASR). To address this issue, we propose a novel backdoor attack method, termed Federated Generative Adversarial Trigger (FedGAT). The proposed method optimizes the trigger by training it with publicly available global models and a small number of samples. It adopts a Generative Adversarial Network (GAN) framework, in which the discriminator is fixed as the converged global model to guide the generator’s training through feedback. As a result, the generator can automatically produce optimized triggers that are highly correlated with the global model’s feature space, effectively reducing the “loss” in backdoor transfer and improving attack performance. Extensive experiments on multiple datasets demonstrate that, without amplifying malicious updates, the proposed method achieves an ASR improvement of 60.95–80.19% over the average baseline performance on the global model, exhibiting outstanding attack capability. Our work raises new challenges for the secure deployment of FL systems.
Tao Liu, Jiguang Lv, D. Man et al.· Cybersecurity· 0 citations
Experimental results demonstrate that the federated LLM-based models consistently outperform a multilayer perceptron baseline, with the LLaMA model achieving up to 99.9% accuracy and F1-score while generalising effectively to previously unseen device types.
Chloe Nazaruk, Rahim Taheri, Gelayol Golcarenarenji et al.· Journal of Supercomputing· 0 citations
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
MIT News · Artificial Intelligence· news.mit.eduAug 24, 2026
