This is a Homepage:

I am a PhD candidate with the School of Cyber Science and Engineering, Shanghai Jiao Tong University.

my head

..

Research subject: Provable security in machine learing.

Publications ((co)first/corresponding-author):

"Laplace Exponential Family Principal Component Analysis",
International Conference on Intelligent Computing (ICIC 2018),
Lecture Notes on Computer Science (LNCS), Springer
"Bayesian Possibilistic C-Means Clustering Screening for Cervical Cancer",
Information Sciences (JCR-Q1).
"Maximizing Influence on Social Networks with Conjugate Learning Automata",
Globecom 2019, SAC::Social Network Track (CCF-C).
"On the Submodularity of Diffusion Models: Equivalent Conditions and Applications",
(pre-print).
"Large-Scale Malicious Software Classification with Fuzzified Features and Boosted Fuzzy Random Forest",
IEEE Transactions on Fuzzy Systems (JCR-Q1, CCF-B).
"Secure Watermark for Deep Neural Networks with Multi-task Learning.",
AAAI2022@SafeAI.
"Persistant Watermark for Image Classification Neural Networks by Penetrating the Autoencoder.",
IEEE ICIP 2021 (CCF-C).
Towards Practical Protocols of Deep Learning Model Watermark for Federated Learning.,
ICMEW2022.
Protecting Deep Cerebrospinal Fluid Cell Imaging Models with Backdoor and Semi-Distillation.,
IEEE DICTA 2021 (Austr. Core B).
Regulating Ownership Verification for Deep Neural Networks: Scenarios, Protocols, and Prospects..
IJCAI 2021@Toward Intellectual Property Protection on Deep Learning as a Services.
Fostering the Robustness of White-box Deep Neural Network Watermarks by Neuron Alignment.,
ICASSP2022 (CCF-B).
Online Intrusion Detection for IoT Systems with Full Bayesian Possibilistic Clustering and Ensembled Fuzzy Classifiers.
IEEE Trans. on Fuzzy Systems (JCR-Q1, CCF-B).
Ownership Verification Protocols for DNN Intellectual Property Protection.
(Book chapter)
PLMmark: A Secure and Robust Black-box Watermarking Framework for Pre-trained Language Models.
AAAI2023 (CCF-A).

Linear Functionality Equivalence Attack against Deep Neural Network Watermarks and a Defense Method by Neuron Mapping.
IEEE TIFS (JCR-Q1, CCF-A).

Solving the Capsulation Attack against Backdoor-based Deep Neural Network Watermarks by Reversing Triggers.
ICASSP2023 (CCF-B).

Revisiting the Information Capacity of Deep Neural Network Watermarks: Upper Bound Estimation and Beyond.
AAAI2024 (CCF-A).

Data-Free Watermark for Deep Neural Networks by Truncated Adversarial Distillation.
ICASSP2024 (CCF-B).

Services:

Reviewer for APSIPA 2019.
Reviewer for ICECCS 2020.
TPC member of APSIPA 2020.
TPC member of APSIPA 2021.
TPC member of APSIPA 2022.
Area Chair of APSIPA 2023.
TPC member of AAAI 2024.
TPC member of ACM MM 2024.
Reviewer for IEEE Transactions on Fuzzy Systems.
Reviewer for IEEE Transactions on Neural Network and Learning Systems.
Reviewer for IEEE Transactions on Information Forensics and Security.
Reviewer for IEEE Transactions on Dependable and Secure Computing.
Reviewer for Pattern Recognition.
Reviewer for IEEE Transcations on Artificial Intelligence.
Reviewer for Information Fusion.
Reviewer for IEEE Transcations on Services Computing.
TA for Information Theory and Encoding (NIS7007), Fall 2020, Fall 2023.
上海交通大学电子信息与电气工程学院B21级033、036、037思政。

Competitions:

The 9th National College Student Information Security Contest (CISCN 2016),
"Deep Learning Based Detection System of Fishing SMS"
First prize nationwide(project competetion), 08/2016.
The 26th Contemporary Undergraduate Mathematical Contest in Modeling (CUMCM 2017),
"Probability-based Scheme for Crowdsourcing Pricing"
Second prize nationwide, First prize in Shanghai division, Top 2 in solving this problem within SJTU, 10/2017.

Open-source and non-profit essays: