Ming Li

Ming Li

Auto-generated profile, based on publicly available information

Ming Li

Jinan University

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
9 August 2023 in Information Sciences
Verified
Journal Article
Closed access
MLMing Li
Ming Li
CZChenyi Zhang
Chenyi Zhang
QLQin Li
Qin Li
SCShuangqin Cheng
Shuangqin Cheng

23 September 2025 in Knowledge-Based Systems
Verified
Journal Article
Open access
MLMing Li
Ming Li
CZChenyi Zhang
Chenyi Zhang
QLQin Li
Qin Li

24 February 2025
Verified
Preprint
Open access
PDF file
MLMing Li
Ming Li
This paper proposes a novel probabilistic neural network for classification that supports continuous incremental learning and unlearning tasks. The proposed method eliminates the need for hyperparameter tuning by relying on a straightforward, data-dr...

28 May 2023 in arXiv
Verified
Preprint
Open access
PDF file
JWJian Weng
Jian Weng
JWJian Weng
Jian Weng
GTGui Tang
Gui Tang
AYAnjia Yang
Anjia Yang
MLMing Li
Ming Li
JLJia-Nan Liu
Jia-Nan Liu
This paper proposes a new approach for privacy-preserving and verifiable convolutional neural network (CNN) testing, enabling a CNN model developer to convince a user of the truthful CNN performance over non-public data from multiple testers, while respecting model privacy. To balance the security and efficiency issues, three new efforts are done by appropriately integrating homomorphic encryption (HE) and zero-knowledge succinct non-interactive argument of knowledge (zk-SNARK) primitives with the CNN testing. First, a CNN model to be tested is strategically partitioned into a private part kept locally by the model developer, and a public part outsourced to an outside server. Then, the private part runs over HE-protected test data sent by a tester and transmits its outputs to the public part for accomplishing subsequent computations of the CNN testing. Second, the correctness of the above CNN testing is enforced by generating zk-SNARK based proofs, with an emphasis on optimizing proving overhead for two-dimensional (2-D) convolution operations, since the operations dominate the performance bottleneck during generating proofs. We specifically present a new quadratic matrix programs (QMPs)-based arithmetic circuit with a single multiplication gate for expressing 2-D convolution operations between multiple filters and inputs in a batch manner. Third, we aggregate multiple proofs with respect to a same CNN model but different testers' test data (i.e., different statements) into one proof, and ensure that the validity of the aggregated proof implies the validity of the original multiple proofs. Lastly, our experimental results demonstrate that our QMPs-based zk-SNARK performs nearly 13.9$\times$faster than the existing QAPs-based zk-SNARK in proving time, and 17.6$\times$faster in Setup time, for high-dimension matrix multiplication.

7 October 2021 in arXiv
Verified
Preprint
Open access
PDF file
MLMing Li
Ming Li
PMPradeep K. Murukannaiah
Pradeep K. Murukannaiah
CJCatholijn M. Jonker
Catholijn M. Jonker
Understanding an opponent agent helps in negotiating with it. Existing works on understanding opponents focus on preference modeling (or estimating the opponent's utility function). An important but largely unexplored direction is recognizing an opponent's negotiation strategy, which captures the opponent's tactics, e.g., to be tough at the beginning but to concede toward the deadline. Recognizing complex, state-of-the-art, negotiation strategies is extremely challenging, and simple heuristics may not be adequate for this purpose. We propose a novel data-driven approach for recognizing an opponent's s negotiation strategy. Our approach includes a data generation method for an agent to generate domain-independent sequences by negotiating with a variety of opponents across domains, a feature engineering method for representing negotiation data as time series with time-step features and overall features, and a hybrid (recurrent neural network-based) deep learning method for recognizing an opponent's strategy from the time series of bids. We perform extensive experiments, spanning four problem scenarios, to demonstrate the effectiveness of our approach.

15 December 2023 in International Journal of Pattern Recognition and Artificial Intelligence
Verified
Journal Article
Closed access
FZFangzhen Zhao
Fangzhen Zhao
CZChenyi Zhang
Chenyi Zhang
NDNaipeng Dong
Naipeng Dong
MLMing Li
Ming Li