Chong Fu
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
Research Subjects
Chong Fu has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Shouling Ji
Zhejiang University, Hangzhou, China
4 shared publications - Xuhong Zhang
Zhejiang University
4 shared publications - Ting Wang
Stony Brook University, Stony Brook, NY, USA
3 shared publications Shouling Ji
2 shared publications- Yiming Wu
Zhejiang University of Technology
2 shared publications - Chenghui Shi
Zhejiang University
1 shared publication
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3250-3264
Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3250-3264
Open AccessUnderstanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications
- 2 August 2024
- Published by Springer Nature
- p. 3-18
SecretKeeper: Robust Vertical Federated Learning Against Label Inference Attacks
- 2 August 2024
- Published by Springer Nature
- p. 3-18
SecretKeeper: Robust Vertical Federated Learning Against Label Inference Attacks
- Open Access
HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
Vertical Federated Learning (VFL) is a trending collaborative machine learning model training solution. Existing industrial frameworks employ secure multi-party computation techniques such as homomorphic encryption to ensure data security and privacy. Despite these efforts, studies have revealed that data leakage remains a risk in VFL due to the correlations between intermediate representations and raw data. Neural networks can accurately capture these correlations, allowing an adversary to reconstruct the data. This emphasizes the need for continued research into securing VFL systems. Our work shows that hashing is a promising solution to counter data reconstruction attacks. The one-way nature of hashing makes it difficult for an adversary to recover data from hash codes. However, implementing hashing in VFL presents new challenges, including vanishing gradients and information loss. To address these issues, we propose HashVFL, which integrates hashing and simultaneously achieves learnability, bit balance, and consistency. Experimental results indicate that HashVFL effectively maintains task performance while defending against data reconstruction attacks. It also brings additional benefits in reducing the degree of label leakage, mitigating adversarial attacks, and detecting abnormal inputs. We hope our work will inspire further research into the potential applications of HashVFL.
Open AccessHashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
Vertical Federated Learning (VFL) is a trending collaborative machine learning model training solution. Existing industrial frameworks employ secure multi-party computation techniques such as homomorphic encryption to ensure data security and privacy. Despite these efforts, studies have revealed that data leakage remains a risk in VFL due to the correlations between intermediate representations and raw data. Neural networks can accurately capture these correlations, allowing an adversary to reconstruct the data. This emphasizes the need for continued research into securing VFL systems. Our work shows that hashing is a promising solution to counter data reconstruction attacks. The one-way nature of hashing makes it difficult for an adversary to recover data from hash codes. However, implementing hashing in VFL presents new challenges, including vanishing gradients and information loss. To address these issues, we propose HashVFL, which integrates hashing and simultaneously achieves learnability, bit balance, and consistency. Experimental results indicate that HashVFL effectively maintains task performance while defending against data reconstruction attacks. It also brings additional benefits in reducing the degree of label leakage, mitigating adversarial attacks, and detecting abnormal inputs. We hope our work will inspire further research into the potential applications of HashVFL.
- 19 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 3435-3450
HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
Vertical Federated Learning (VFL) is a trending collaborative machine learning model training solution. Existing industrial frameworks employ secure multi-party computation techniques such as homomorphic encryption to ensure data security and privacy. Despite these efforts, studies have revealed that data leakage remains a risk in VFL due to the correlations between intermediate representations and raw data. Neural networks can accurately capture these correlations, allowing an adversary to reconstruct the data. This emphasizes the need for continued research into securing VFL systems. Our work shows that hashing is a promising solution to counter data reconstruction attacks. The one-way nature of hashing makes it difficult for an adversary to recover data from hash codes. However, implementing hashing in VFL presents new challenges, including vanishing gradients and information loss. To address these issues, we propose HashVFL, which integrates hashing and simultaneously achieves learnability, bit balance, and consistency. Experimental results indicate that HashVFL effectively maintains task performance while defending against data reconstruction attacks. It also brings additional benefits in reducing the degree of label leakage, mitigating adversarial attacks, and detecting abnormal inputs. We hope our work will inspire further research into the potential applications of HashVFL.
- 19 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 19 (15566013) , 3435-3450
HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
Vertical Federated Learning (VFL) is a trending collaborative machine learning model training solution. Existing industrial frameworks employ secure multi-party computation techniques such as homomorphic encryption to ensure data security and privacy. Despite these efforts, studies have revealed that data leakage remains a risk in VFL due to the correlations between intermediate representations and raw data. Neural networks can accurately capture these correlations, allowing an adversary to reconstruct the data. This emphasizes the need for continued research into securing VFL systems. Our work shows that hashing is a promising solution to counter data reconstruction attacks. The one-way nature of hashing makes it difficult for an adversary to recover data from hash codes. However, implementing hashing in VFL presents new challenges, including vanishing gradients and information loss. To address these issues, we propose HashVFL, which integrates hashing and simultaneously achieves learnability, bit balance, and consistency. Experimental results indicate that HashVFL effectively maintains task performance while defending against data reconstruction attacks. It also brings additional benefits in reducing the degree of label leakage, mitigating adversarial attacks, and detecting abnormal inputs. We hope our work will inspire further research into the potential applications of HashVFL.
- Open Access
FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases
Trojan attack on deep neural networks, also known as backdoor attack, is a typical threat to artificial intelligence. A trojaned neural network behaves normally with clean inputs. However, if the input contains a particular trigger, the trojaned model will have attacker-chosen abnormal behavior. Although many backdoor detection methods exist, most of them assume that the defender has access to a set of clean validation samples or samples with the trigger, which may not hold in some crucial real-world cases, e.g., the case where the defender is the maintainer of model-sharing platforms. Thus, in this paper, we propose FreeEagle, the first data-free backdoor detection method that can effectively detect complex backdoor attacks on deep neural networks, without relying on the access to any clean samples or samples with the trigger. The evaluation results on diverse datasets and model architectures show that FreeEagle is effective against various complex backdoor attacks, even outperforming some state-of-the-art non-data-free backdoor detection methods.
Open AccessFreeEagle: Detecting Complex Neural Trojans in Data-Free Cases
Trojan attack on deep neural networks, also known as backdoor attack, is a typical threat to artificial intelligence. A trojaned neural network behaves normally with clean inputs. However, if the input contains a particular trigger, the trojaned model will have attacker-chosen abnormal behavior. Although many backdoor detection methods exist, most of them assume that the defender has access to a set of clean validation samples or samples with the trigger, which may not hold in some crucial real-world cases, e.g., the case where the defender is the maintainer of model-sharing platforms. Thus, in this paper, we propose FreeEagle, the first data-free backdoor detection method that can effectively detect complex backdoor attacks on deep neural networks, without relying on the access to any clean samples or samples with the trigger. The evaluation results on diverse datasets and model architectures show that FreeEagle is effective against various complex backdoor attacks, even outperforming some state-of-the-art non-data-free backdoor detection methods.