Rongke Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Rongke Liu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Dong Wang
School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China
2 shared publications - Youwen Zhu
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China
2 shared publications - Gaoning Pan
School of Cyberspace, Hangzhou Dianzi University
1 shared publication Kaitian Guo
School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China
1 shared publication- Lei Zhou
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China
1 shared publication Qianqian Qin
School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China
1 shared publication
Latest Publications
- 19 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2342-2357
Model Inversion Attack Against Federated Unlearning
In response to emerging regulations on the “right to be forgotten”, federated unlearning (FU) has been proposed to ensure privacy compliance by efficiently eliminating the influence of specific data from federated learning (FL) models. However, existing FU studies primarily focus on improving unlearning efficiency, with little attention given to the potential privacy risks introduced by FU itself. To bridge this research gap, we propose a novel federated unlearning inversion attack (FUIA) to expose potential privacy leakage in FU. This work represents the first systematic study on the privacy vulnerabilities inherent in FU. FUIA can apply to three major FU scenarios: sample unlearning, client unlearning, and class unlearning, demonstrating broad applicability and threat potential. Specifically, the server, acting as an honest-but-curious attacker, continuously records model parameter changes throughout the unlearning process and analyzes the differences before and after unlearning to infer the gradient information of forgotten data, enabling the reconstruction of its features or labels. FUIA directly undermines the goal of FU to eliminate the influence of specific data, exploiting vulnerabilities in the FU process to reconstruct forgotten data, thereby revealing flaws in privacy protection. Moreover, we explore two potential defense strategies that introduce a trade-off between privacy protection and model performance. Extensive experiments on multiple benchmark datasets and various FU methods demonstrate that FUIA effectively reveals private information of forgotten data.
- 19 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2342-2357
Model Inversion Attack Against Federated Unlearning
In response to emerging regulations on the “right to be forgotten”, federated unlearning (FU) has been proposed to ensure privacy compliance by efficiently eliminating the influence of specific data from federated learning (FL) models. However, existing FU studies primarily focus on improving unlearning efficiency, with little attention given to the potential privacy risks introduced by FU itself. To bridge this research gap, we propose a novel federated unlearning inversion attack (FUIA) to expose potential privacy leakage in FU. This work represents the first systematic study on the privacy vulnerabilities inherent in FU. FUIA can apply to three major FU scenarios: sample unlearning, client unlearning, and class unlearning, demonstrating broad applicability and threat potential. Specifically, the server, acting as an honest-but-curious attacker, continuously records model parameter changes throughout the unlearning process and analyzes the differences before and after unlearning to infer the gradient information of forgotten data, enabling the reconstruction of its features or labels. FUIA directly undermines the goal of FU to eliminate the influence of specific data, exploiting vulnerabilities in the FU process to reconstruct forgotten data, thereby revealing flaws in privacy protection. Moreover, we explore two potential defense strategies that introduce a trade-off between privacy protection and model performance. Extensive experiments on multiple benchmark datasets and various FU methods demonstrate that FUIA effectively reveals private information of forgotten data.
- 5 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 3958-3973
Unstoppable Attack: Label-Only Model Inversion Via Conditional Diffusion Model
Model inversion attacks (MIAs) aim to recover private data from inaccessible training sets of deep learning models, posing a privacy threat. MIAs primarily focus on the white-box scenario where attackers have full access to the model’s structure and parameters. However, practical applications are usually in black-box scenarios or label-only scenarios, i.e., the attackers can only obtain the output confidence vectors or labels by accessing the model. Therefore, the attack models in existing MIAs are difficult to effectively train with the knowledge of the target model, resulting in sub-optimal attacks. To the best of our knowledge, we pioneer the research of a powerful and practical attack model in the label-only scenario. In this paper, we develop a novel MIA method, leveraging a conditional diffusion model (CDM) to recover representative samples under the target label from the training set. Two techniques are introduced: selecting an auxiliary dataset relevant to the target model task and using predicted labels as conditions to guide training CDM; and inputting target label, pre-defined guidance strength, and random noise into the trained attack model to generate and correct multiple results for final selection. This method is evaluated using Learned Perceptual Image Patch Similarity as a new metric and as a judgment basis for deciding the values of hyper-parameters. Experimental results show that this method can generate similar and accurate samples to the target label, outperforming generators of previous approaches.
- 5 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 3958-3973
Unstoppable Attack: Label-Only Model Inversion Via Conditional Diffusion Model
Model inversion attacks (MIAs) aim to recover private data from inaccessible training sets of deep learning models, posing a privacy threat. MIAs primarily focus on the white-box scenario where attackers have full access to the model’s structure and parameters. However, practical applications are usually in black-box scenarios or label-only scenarios, i.e., the attackers can only obtain the output confidence vectors or labels by accessing the model. Therefore, the attack models in existing MIAs are difficult to effectively train with the knowledge of the target model, resulting in sub-optimal attacks. To the best of our knowledge, we pioneer the research of a powerful and practical attack model in the label-only scenario. In this paper, we develop a novel MIA method, leveraging a conditional diffusion model (CDM) to recover representative samples under the target label from the training set. Two techniques are introduced: selecting an auxiliary dataset relevant to the target model task and using predicted labels as conditions to guide training CDM; and inputting target label, pre-defined guidance strength, and random noise into the trained attack model to generate and correct multiple results for final selection. This method is evaluated using Learned Perceptual Image Patch Similarity as a new metric and as a judgment basis for deciding the values of hyper-parameters. Experimental results show that this method can generate similar and accurate samples to the target label, outperforming generators of previous approaches.