Miseon Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Miseon Yu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Younghan Lee
Department of Convergence Security Engineering, Sungshin Womens University, Seoul, Republic of Korea
3 shared publications - Yunheung Paek
Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea
3 shared publications - Woorim Han
Seoul National University
2 shared publications - Yungi Cho
Seoul National University
2 shared publications - Ho Bae
Department of Cyber Security Ewha Womans University
1 shared publication - Hyungon Moon
Ulsan National Institute of Science and Technology (UNIST), Ulsan, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 5 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 101398-101414
PI-FD: Property Inference Attacks on Federated Learning With Distillation via Synthetic Data Generation
Federated Learning with Distillation (FD) has clients upload output logits evaluated on a shared public dataset, instead of gradients computed on private data. Although FD is often believed to offer stronger privacy protection than traditional federated learning, recent studies have shown that a malicious server can still extract sensitive information, such as reconstructing private samples or inferring label distributions in a private dataset [1], [2]. This suggests that FD is not immune to sensitive information leakages, raising concerns of other significant privacy threats such as property inference attacks. Motivated by these concerns, we explore property inference attacks (PIA) which aim to infer property population information (e.g., demographics or disease prevalence) of a private dataset. However, most existing PIA methods rely on the same underlying distribution as the victim’s private data, which is often unavailable in FD because the server only observes the public dataset distribution. This distribution shift can significantly degrade the effectiveness of existing PIA methods. To overcome this limitation, we introduce PI-FD, a new PIA method that employs synthetic data generation in combination with novel loss functions. Experiments on four datasets with 14 properties show PI-FD reaches 94.07% attack accuracy, highlighting the need to mitigate PIA threats.
- 5 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 101398-101414
Open AccessPI-FD: Property Inference Attacks on Federated Learning With Distillation via Synthetic Data Generation
Federated Learning with Distillation (FD) has clients upload output logits evaluated on a shared public dataset, instead of gradients computed on private data. Although FD is often believed to offer stronger privacy protection than traditional federated learning, recent studies have shown that a malicious server can still extract sensitive information, such as reconstructing private samples or inferring label distributions in a private dataset [1], [2]. This suggests that FD is not immune to sensitive information leakages, raising concerns of other significant privacy threats such as property inference attacks. Motivated by these concerns, we explore property inference attacks (PIA) which aim to infer property population information (e.g., demographics or disease prevalence) of a private dataset. However, most existing PIA methods rely on the same underlying distribution as the victim’s private data, which is often unavailable in FD because the server only observes the public dataset distribution. This distribution shift can significantly degrade the effectiveness of existing PIA methods. To overcome this limitation, we introduce PI-FD, a new PIA method that employs synthetic data generation in combination with novel loss functions. Experiments on four datasets with 14 properties show PI-FD reaches 94.07% attack accuracy, highlighting the need to mitigate PIA threats.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1069-1082
Rethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability Repair
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1069-1082
Open AccessRethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability Repair
- 5 September 2024
- Published by Springer Nature
- p. 291-312
VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification
- 5 September 2024
- Published by Springer Nature
- p. 291-312
VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification