Min Chen
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
Min Chen has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Zhikun Zhang
Zhejiang University, Hangzhou, China
9 shared publications - Linkang Du
Xi'an Jiaotong University, Xi'an, China
6 shared publications - Jiming Chen
Zhejiang University, Hangzhou, China
4 shared publications - Peng Cheng
Zhejiang University, Hangzhou, China
4 shared publications - Mingyang Sun
Peking University
3 shared publications - Yunjun Gao
Zhejiang University, Hangzhou, China
3 shared publications
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 48-62
SEAL: Reinforcing Global Safety in Mixture-of-Experts through S hared E xpert AL ignment
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 48-62
Open AccessSEAL: Reinforcing Global Safety in Mixture-of-Experts through S hared E xpert AL ignment
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5121-5135
NotaryMark: Multi-Bit Watermarking for Black-Box Dataset Usage Auditing in Text-to-Image Diffusion Models
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5121-5135
Open AccessNotaryMark: Multi-Bit Watermarking for Black-Box Dataset Usage Auditing in Text-to-Image Diffusion Models
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5106-5120
DWBench: Holistic Evaluation of Watermark for Dataset Copyright Auditing
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5106-5120
Open AccessDWBench: Holistic Evaluation of Watermark for Dataset Copyright Auditing
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4687-4701
InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4687-4701
Open AccessInceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (11) , 7461-7477
Efficient Poisoning Attacks Against Reinforcement Learning-Based Recommender Systems
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (11) , 7461-7477
Efficient Poisoning Attacks Against Reinforcement Learning-Based Recommender Systems
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (1) , 1514-1527
Revealing the Risk of Hyper-Parameter Leakage in Deep Reinforcement Learning Models
Deep reinforcement learning (DRL) has been implemented across various critical applications, including smart grids, trac management systems, and autonomous vehicles. To safeguard intellectual property and mitigate security vulnerabilities, access to DRL models is typically restricted to a black-box format. is means specic details like the structure of the policy network and optimization processes are not openly available to users. It is crucial to determine if the hyper-parameters can be inferred from observable states and actions within these models, presenting two primary challenges: 1) limited data available from the black-box model and 2) the intertwined eects of hyperparameters on the model's behavior. Since DRL models exhibit varying behaviors in identical tasks depending on their hyper-parameter congurations, we introduce a novel hyper-parameter inference attack against DRL, named HyperInfer, which allows adversaries to deduce the settings of a black-box DRL model. In order to fully assess the risk of model hyper-parameter leakage, we design two novel state generation methods that provoke divergent responses from DRL models. We also develop an inference framework to elucidate the relationship between model behavior and hyper-parameter settings. rough comprehensive experiments involving multiple DRL models and environments, we demonstrate that model behaviors can indeed reveal hyper-parameter settings, with inference accuracy surpassing 90% in scenarios such as PPO with CartPole. We also discuss keyndings relevant to practical applications and explore how knowledge of hyperparameters can facilitate more sophisticated attacks. Lastly, we propose potential defensive strategies to minimize the risk of hyper-parameter leakage in DRL models.
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (1) , 1514-1527
Revealing the Risk of Hyper-Parameter Leakage in Deep Reinforcement Learning Models
Deep reinforcement learning (DRL) has been implemented across various critical applications, including smart grids, trac management systems, and autonomous vehicles. To safeguard intellectual property and mitigate security vulnerabilities, access to DRL models is typically restricted to a black-box format. is means specic details like the structure of the policy network and optimization processes are not openly available to users. It is crucial to determine if the hyper-parameters can be inferred from observable states and actions within these models, presenting two primary challenges: 1) limited data available from the black-box model and 2) the intertwined eects of hyperparameters on the model's behavior. Since DRL models exhibit varying behaviors in identical tasks depending on their hyper-parameter congurations, we introduce a novel hyper-parameter inference attack against DRL, named HyperInfer, which allows adversaries to deduce the settings of a black-box DRL model. In order to fully assess the risk of model hyper-parameter leakage, we design two novel state generation methods that provoke divergent responses from DRL models. We also develop an inference framework to elucidate the relationship between model behavior and hyper-parameter settings. rough comprehensive experiments involving multiple DRL models and environments, we demonstrate that model behaviors can indeed reveal hyper-parameter settings, with inference accuracy surpassing 90% in scenarios such as PPO with CartPole. We also discuss keyndings relevant to practical applications and explore how knowledge of hyperparameters can facilitate more sophisticated attacks. Lastly, we propose potential defensive strategies to minimize the risk of hyper-parameter leakage in DRL models.
- Open Access
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2500-2513
ArtistAuditor: Auditing Artist Style Pirate in Text-to-Image Generation Models
- 22 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 2500-2513
Open AccessArtistAuditor: Auditing Artist Style Pirate in Text-to-Image Generation Models
- Open Access
- 1 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1331-1344
PARL: Poisoning Attacks Against Reinforcement Learning-based Recommender Systems
Recommender systems predict and suggest relevant options to users in various domains, such as e-commerce, streaming services, and social media. Recently, deep reinforcement learning (DRL)-based recommendation systems have become increasingly popular in academics and industry since DRL can characterize the long-term interaction between the system and users to achieve a better recommendation experience, e.g., Netflix, Spotify, Google, and YouTube. This paper demonstrates that an adversary can manipulate the DRL-based recommender system by injecting carefully designed user-system interaction records. The poisoning attack against the DRL-based recommender system is formulated as a non-convex integer programming problem. To solve the problem, we proposed a three-phase mechanism (called PARL) to maximize the hit ratio (the proportion of recommendations that result in actual user interactions, such as clicks, purchases, or other relevant actions) while avoiding easy detection. The core idea of PARL is to improve the ranking of the target item while fixing the rankings of other items. Considering the sequential decision-making characteristics of DRL, PARL rearranges the items' order of the fake users to mimic the normal users' sequential features, an aspect usually overlooked in existing work. Our experiments on three real-world datasets demonstrate the effectiveness of PARL and better concealment against the detection techniques. PARL is open-sourced at https://github.com/PARL-RS/PARL.
- 1 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1331-1344
Open AccessPARL: Poisoning Attacks Against Reinforcement Learning-based Recommender Systems
Recommender systems predict and suggest relevant options to users in various domains, such as e-commerce, streaming services, and social media. Recently, deep reinforcement learning (DRL)-based recommendation systems have become increasingly popular in academics and industry since DRL can characterize the long-term interaction between the system and users to achieve a better recommendation experience, e.g., Netflix, Spotify, Google, and YouTube. This paper demonstrates that an adversary can manipulate the DRL-based recommender system by injecting carefully designed user-system interaction records. The poisoning attack against the DRL-based recommender system is formulated as a non-convex integer programming problem. To solve the problem, we proposed a three-phase mechanism (called PARL) to maximize the hit ratio (the proportion of recommendations that result in actual user interactions, such as clicks, purchases, or other relevant actions) while avoiding easy detection. The core idea of PARL is to improve the ranking of the target item while fixing the rankings of other items. Considering the sequential decision-making characteristics of DRL, PARL rearranges the items' order of the fake users to mimic the normal users' sequential features, an aspect usually overlooked in existing work. Our experiments on three real-world datasets demonstrate the effectiveness of PARL and better concealment against the detection techniques. PARL is open-sourced at https://github.com/PARL-RS/PARL.
- Open Access
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 2621-2635
DPMLBench: Holistic Evaluation of Differentially Private Machine Learning
Differential privacy (DP), as a rigorous mathematical definition quantifying privacy leakage, has become a well-accepted standard for privacy protection. Combined with powerful machine learning (ML) techniques, differentially private machine learning (DPML) is increasingly important. As the most classic DPML algorithm, DP-SGD incurs a significant loss of utility, which hinders DPML's deployment in practice. Many studies have recently proposed improved algorithms based on DP-SGD to mitigate utility loss. However, these studies are isolated and cannot comprehensively measure the performance of improvements proposed in algorithms. More importantly, there is a lack of comprehensive research to compare improvements in these DPML algorithms across utility, defensive capabilities, and generalizability. We fill this gap by performing a holistic measurement of improved DPML algorithms on utility and defense capability against membership inference attacks (MIAs) on image classification tasks. We first present a taxonomy of where improvements are located in the ML life cycle. Based on our taxonomy, we jointly perform an extensive measurement study of the improved DPML algorithms, over twelve algorithms, four model architectures, four datasets, two attacks, and various privacy budget configurations. We also cover state-of-the-art label differential privacy (Label DP) algorithms in the evaluation. According to our empirical results, DP can effectively defend against MIAs, and sensitivity-bounding techniques such as per-sample gradient clipping play an important role in defense. We also explore some improvements that can maintain model utility and defend against MIAs more effectively. Experiments show that Label DP algorithms achieve less utility loss but are fragile to MIAs. ML practitioners may benefit from these evaluations to select appropriate algorithms. To support our evaluation, we implement a modular re-usable software, DPMLBench,1. We open-source the tool in https://github.com/DmsKinson/DPMLBench which enables sensitive data owners to deploy DPML algorithms and serves as a benchmark tool for researchers and practitioners.
- 15 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 2621-2635
Open AccessDPMLBench: Holistic Evaluation of Differentially Private Machine Learning
Differential privacy (DP), as a rigorous mathematical definition quantifying privacy leakage, has become a well-accepted standard for privacy protection. Combined with powerful machine learning (ML) techniques, differentially private machine learning (DPML) is increasingly important. As the most classic DPML algorithm, DP-SGD incurs a significant loss of utility, which hinders DPML's deployment in practice. Many studies have recently proposed improved algorithms based on DP-SGD to mitigate utility loss. However, these studies are isolated and cannot comprehensively measure the performance of improvements proposed in algorithms. More importantly, there is a lack of comprehensive research to compare improvements in these DPML algorithms across utility, defensive capabilities, and generalizability. We fill this gap by performing a holistic measurement of improved DPML algorithms on utility and defense capability against membership inference attacks (MIAs) on image classification tasks. We first present a taxonomy of where improvements are located in the ML life cycle. Based on our taxonomy, we jointly perform an extensive measurement study of the improved DPML algorithms, over twelve algorithms, four model architectures, four datasets, two attacks, and various privacy budget configurations. We also cover state-of-the-art label differential privacy (Label DP) algorithms in the evaluation. According to our empirical results, DP can effectively defend against MIAs, and sensitivity-bounding techniques such as per-sample gradient clipping play an important role in defense. We also explore some improvements that can maintain model utility and defend against MIAs more effectively. Experiments show that Label DP algorithms achieve less utility loss but are fragile to MIAs. ML practitioners may benefit from these evaluations to select appropriate algorithms. To support our evaluation, we implement a modular re-usable software, DPMLBench,1. We open-source the tool in https://github.com/DmsKinson/DPMLBench which enables sensitive data owners to deploy DPML algorithms and serves as a benchmark tool for researchers and practitioners.
- Open Access
- 12 November 2021
- Published by Association for Computing Machinery (ACM)
- p. 896-911
When Machine Unlearning Jeopardizes Privacy
The right to be forgotten states that a data owner has the right to erase their data from an entity storing it. In the context of machine learning (ML), the right to be forgotten requires an ML model owner to remove the data owner's data from the training set used to build the ML model, a process known asmachine unlearning. While originally designed to protect the privacy of the data owner, we argue that machine unlearning may leave some imprint of the data in the ML model and thus create unintended privacy risks. In this paper, we perform the first study on investigating the unintended information leakage caused by machine unlearning. We propose a novel membership inference attack that leverages the different outputs of an ML model's two versions to infer whether a target sample is part of the training set of the original model but out of the training set of the corresponding unlearned model. Our experiments demonstrate that the proposed membership inference attack achieves strong performance. More importantly, we show that our attack in multiple cases outperforms the classical membership inference attack on the original ML model, which indicates that machine unlearning can have counterproductive effects on privacy. We notice that the privacy degradation is especially significant for well-generalized ML models where classical membership inference does not perform well. We further investigate four mechanisms to mitigate the newly discovered privacy risks and show that releasing the predicted label only, temperature scaling, and differential privacy are effective. We believe that our results can help improve privacy protection in practical implementations of machine unlearning. \footnoteOur code is available at \urlhttps://github.com/MinChen00/UnlearningLeaks.
- 12 November 2021
- Published by Association for Computing Machinery (ACM)
- p. 896-911
Open AccessWhen Machine Unlearning Jeopardizes Privacy
The right to be forgotten states that a data owner has the right to erase their data from an entity storing it. In the context of machine learning (ML), the right to be forgotten requires an ML model owner to remove the data owner's data from the training set used to build the ML model, a process known asmachine unlearning. While originally designed to protect the privacy of the data owner, we argue that machine unlearning may leave some imprint of the data in the ML model and thus create unintended privacy risks. In this paper, we perform the first study on investigating the unintended information leakage caused by machine unlearning. We propose a novel membership inference attack that leverages the different outputs of an ML model's two versions to infer whether a target sample is part of the training set of the original model but out of the training set of the corresponding unlearned model. Our experiments demonstrate that the proposed membership inference attack achieves strong performance. More importantly, we show that our attack in multiple cases outperforms the classical membership inference attack on the original ML model, which indicates that machine unlearning can have counterproductive effects on privacy. We notice that the privacy degradation is especially significant for well-generalized ML models where classical membership inference does not perform well. We further investigate four mechanisms to mitigate the newly discovered privacy risks and show that releasing the predicted label only, temperature scaling, and differential privacy are effective. We believe that our results can help improve privacy protection in practical implementations of machine unlearning. \footnoteOur code is available at \urlhttps://github.com/MinChen00/UnlearningLeaks.