Chunyi Zhou

Chunyi Zhou

Auto-generated profile, based on publicly available information

Chunyi Zhou

Zhejiang University

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 April 2020 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
CZChunyi Zhou
Chunyi Zhou
AFAnmin Fu
Anmin Fu
SYShui Yu
Shui Yu
WYWei Yang
Wei Yang
CLChangfeng Li
Changfeng Li
YZYuqing Zhang
Yuqing Zhang
Federated learning can combine a large number of scattered user groups and train models collaboratively without uploading data sets, so as to avoid the server collecting user sensitive data. However, the model of federated learning will expose the training set information of users, and the uneven amount of data owned by users in multiple users’ scenarios will lead to the inefficiency of training. In this paper, we propose a privacy-preserving federated learning scheme in fog computing. Acting as a participant, each fog node is enabled to collect Internet of Things (IoT) device data and complete the learning task in our scheme. Such design effectively improves the low training efficiency and model accuracy caused by the uneven distribution of data and the large gap of computing power. We enable IoT device data to satisfy ε-differential privacy to resist data attacks and leverage the combination of blinding and Paillier homomorphic encryption against model attacks, which realize the security aggregation of model parameters. In addition, we formally verified our scheme can not only guarantee both data security and model security, but completely resist collusion attacks launched by multiple malicious entities. Our experiments based on the Fashion-MNIST dataset prove that our scheme is highly efficient in practice.

11 February 2025 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
NLNa Li
Na Li
CZChunyi Zhou
Chunyi Zhou
YGYansong Gao
Yansong Gao
HCHui Chen
Hui Chen
ZZZhi Zhang
Zhi Zhang
AFAnmin Fu
Anmin Fu
Personal digital data is a critical asset, and governments worldwide have enforced laws and regulations to protect data privacy. Data users have been endowed with the “right to be forgotten” (RTBF) of their data. In the course of machine learning (ML), the forgotten right requires a model provider to delete user data and its subsequent impact on ML models upon user requests. Machine unlearning (MU) emerges to address this, which has garnered ever-increasing attention from both industry and academia. Specifically, MU allows model providers to eliminate the influence of unlearned data without retraining the model from scratch, ensuring the model behaves as if it never encountered this data. While the area has developed rapidly, there is a lack of comprehensive surveys to capture the latest advancements. Recognizing this shortage, we conduct an extensive exploration to map the landscape of MU including the (fine-grained) taxonomy of unlearning algorithms under centralized and distributed settings, debate on approximate unlearning, verification and evaluation metrics, and challenges and solutions across various applications. We also focus on the motivations, challenges, and specific methods for deploying unlearning in large language models (LLMs), as well as the potential attacks targeting unlearning processes. The survey concludes by outlining potential directions for future research, hoping to serve as a beacon for interested scholars.

1 January 2025
Verified
Conference Paper
Open access
PDF file
HAHengyu An
Hengyu An
JZJinghuai Zhang
Jinghuai Zhang
TDTianyu Du
Tianyu Du
CZChunyi Zhou
Chunyi Zhou
QLQingming Li
Qingming Li
SJShouling Ji
Shouling Ji
Hengyu An, Jinghuai Zhang, Tianyu Du, Chunyi Zhou, Qingming Li, Tao Lin, Shouling Ji. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

30 April 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
CZChunyi Zhou
Chunyi Zhou
YGYansong Gao
Yansong Gao
AFAnmin Fu
Anmin Fu
KCKai Chen
Kai Chen
ZZZhi Zhang
Zhi Zhang
YZYuqing Zhang
Yuqing Zhang
The right to be forgotten has incentivized machine unlearning, but a key challenge persists: the lack of reliable methods to verify unlearning conducted by model providers. This gap facilitates dishonest model providers to deceive data contributors. Current approaches often rely on invasive methods like backdoor injection. However, it poses security concerns and is also inapplicable to legacy data—already released data. To tackle this challenge, this work initializes the first non-invasive unlearning verification framework which operates at triple-granularity (class-, volume-, sample-level) to assess the data facticity and volume integrity of machine unlearning. In this paper, we propose a framework, named TruVRF, encompasses three Unlearning-Metrics, each tailored to counter different types of dishonest model providers or servers (Neglecting Server, Lazy Server, Deceiving Server). TruVRF leverages non-invasive model sensitivity to enable multi-granularity verification of unlearning. Specifically, Unlearning-Metric-I checks if the removed class matches the data contributor’s unlearning request, Unlearning-Metric-II measures the amount of unlearned data, and Unlearning-Metric-III validates the correspondence of a specific unlearned sample with the requested deletion. We conducted extensive evaluations of TruVRF efficacy across three datasets, and notably, we also evaluated the effectiveness and computational overhead of TruVRF in real-world applications for the face recognition dataset. Our experimental results demonstrate that TruVRF achieves robust verification performance: Unlearning-Metric-I and -III achieve over 90% verification accuracy on average against dishonest servers, while Unlearning-Metric-II maintains an inference deviation within 4.8% to 8.2%. Additionally, TruVRF demonstrates generalizability across diverse conditions, including varying numbers of unlearned classes and sample volumes. Significantly, TruVRF is applied to two state-of-theart unlearning frameworks: SISA [3] (presented at Oakland’21) and Amnesiac Unlearning [18], representing exact and approximate unlearning methods, respectively, which affirm TruVRF’s practicality. In addition, we conducted extensive evaluations around TruVRF, including ablation experiments, trade-offs in computational overhead, and the robustness of model sensitivity, among others.

14 November 2024 in arXiv
Verified
Preprint
Open access
PDF file
YGYuyou Gan
Yuyou Gan
YYYong Yang
Yong Yang
ZMZhe Ma
Zhe Ma
PHPing He
Ping He
RZRui Zeng
Rui Zeng
SJShouling Ji
Shouling Ji
With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as their control hub. While LLMs have achieved success in various tasks, they face numerous security and privacy threats, which become even more severe in the agent scenarios. To enhance the reliability of LLM-based applications, a range of research has emerged to assess and mitigate these risks from different perspectives. To help researchers gain a comprehensive understanding of various risks, this survey collects and analyzes the different threats faced by these agents. To address the challenges posed by previous taxonomies in handling cross-module and cross-stage threats, we propose a novel taxonomy framework based on the sources and impacts. Additionally, we identify six key features of LLM-based agents, based on which we summarize the current research progress and analyze their limitations. Subsequently, we select four representative agents as case studies to analyze the risks they may face in practical use. Finally, based on the aforementioned analyses, we propose future research directions from the perspectives of data, methodology, and policy, respectively.

12 December 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
ZDZhiyang Dai
Zhiyang Dai
YGYansong Gao
Yansong Gao
CZChunyi Zhou
Chunyi Zhou
AFAnmin Fu
Anmin Fu
ZZZhi Zhang
Zhi Zhang
YZYuqing Zhang
Yuqing Zhang
In contrast to prevalent Federated Learning (FL) privacy inference techniques such as generative adversarial networks attacks, membership inference attacks, property inference attacks, and model inversion attacks, we devise an innovative privacy threat: the Data Distribution Decompose Attack on FL, termed Decaf. This attack enables an honest-but-curious FL server to meticulously profile the proportion of each class owned by the victim FL user, divulging sensitive information like local market item distribution and business competitiveness. The crux of Decaf lies in the profound observation that the magnitude of local model gradient changes closely mirrors the underlying data distribution, including the proportion of each class. Decaf addresses two crucial challenges: accurately identify the missing/null class(es) given by any victim user as a premise and then quantify the precise relationship between gradient changes and each remaining non-null class. Notably, Decaf operates stealthily, rendering it entirely passive and undetectable to victim users regarding the infringement of their data distribution privacy. Experimental validation on five benchmark datasets (MNIST, FASHION-MNIST, CIFAR-10, FER-2013, and SkinCancer) employing diverse model architectures, including customized convolutional networks, standardized VGG16, and ResNet18, demonstrates Decaf’s efficacy. Results indicate its ability to accurately decompose local user data distribution, regardless of whether it is IID or non-IID distributed. Specifically, the dissimilarity measured using L ∞ distance between the distribution decomposed by Decaf and ground truth is consistently below 5% when no null classes exist. Moreover, Decaf achieves 100% accuracy in determining any victim user’s null classes, validated through formal proof.