HASSLE: A Self-Supervised Learning Enhanced Hijacking Attack on Vertical Federated Learning

arXiv 2507.10162 ↗First posted 14 Jul 2025cs.CRcited by 0

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Vertical Federated Learning (VFL) enables an orchestrating active party to perform a machine learning task by cooperating with passive parties that provide additional task-related features for the same training data entities. While prior research has leveraged the privacy vulnerability of VFL to compromise its integrity through a combination of label inference and backdoor attacks, their effectiveness is constrained by the low label inference precision and suboptimal backdoor injection conditions. To facilitate a more rigorous security evaluation on VFL without these limitations, we propose HASSLE, a hijacking attack framework composed of a gradient-direction-based label inference module and an adversarial embedding generation algorithm enhanced by self-supervised learning. HASSLE accurately identifies private samples associated with a targeted label using only a single known instance of that label. In the two-party scenario, it demonstrates strong performance with an attack success rate (ASR) of over 99% across four datasets, including both image and tabular modalities, and achieves 85% ASR on the more complex CIFAR-100 dataset. Evaluation of HASSLE against 8 potential defenses further highlights its significant threat while providing new insights into building a trustworthy VFL system.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 18 of its 31 references that are in the map. First posted on arXiv 14 Jul 2025.

Builds on

18 of 31 references.

References · 18

2014Explaining and Harnessing Adversarial Examplescited by 7,364
2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
2016Deep Learning with Differential Privacycited by 2,728
2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
2021Anti-Backdoor Learning: Training Clean Models on Poisoned Datacited by 263
2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 235
2021SCARF: Self-Supervised Contrastive Learning using Random Feature Corruptioncited by 156
2021Federated Learning for Open Bankingcited by 141
2022Vertical Federated Learning: Concepts, Advances and Challengescited by 108
2021Label Leakage and Protection in Two-party Split Learningcited by 90
2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84

6 more

2022Label Leakage and Protection from Forward Embedding in Vertical Federated Learningcited by 27
2023BadVFL: Backdoor Attacks in Vertical Federated Learningcited by 10
2022ADI: Adversarial Dominating Inputs in Vertical Federated Learning Systemscited by 9
2023Practical and General Backdoor Attacks against Vertical Federated Learningcited by 6
2022Hijack Vertical Federated Learning Models As One Partycited by 5
2024VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purificationcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way