Data Leakage
Data Leakage is a phenomenon in machine learning wherein information from outside the training dataset or future time periods inadvertently influences the model during training, leading to overly optimistic performance estimates and invalid generalization assessment.
622
Publications
38.4K
Citations
2.3K
Authors
840
Institutions
Publications per year
2017–2026
461
Parents
622
Membership Inference Attacks Against Machine Learning Models
Reza Shokri, Marco Stronati, Congzheng Song et al. · 2017 · 4.2K citations
Leakage and the reproducibility crisis in machine-learning-based science
Sayash Kapoor, Arvind Narayanan · Patterns · 2023 · 671 citations · Full text
1–5 of 622
2.3K
National Institute of Technology Kurukshetra, India
13 publications · 411 citations
13
h-index
13
h-index
7
h-index
6
h-index
5
h-index
1–5 of 2.3K
840
Nanyang Technological University
Singapore, Singapore
13 h-index
23 publications
1.2K citations

Beijing University of Posts and Telecommunications
Beijing, China
13 h-index
32 publications
4K citations

Cornell University
Ithaca, United States
11 h-index
25 publications
15.6K citations
Tsinghua University
Beijing, China
10 h-index
21 publications
639 citations

Chinese Academy of Sciences
Beijing, China
10 h-index
31 publications
1.1K citations
National Institute of Technology Kurukshetra
Kurukshetra, India
10 h-index
23 publications
701 citations

Pennsylvania State University
State College, United States
9 h-index
21 publications
370 citations

Data61
Sydney, Australia
9 h-index
11 publications
931 citations
1–8 of 840
Repository · 48 publications · 1.8K citations
22
h-index
19 publications · 1.1K citations
16
h-index
12 publications · 1.4K citations
12
h-index
12 publications · 1.9K citations
12
h-index
5 publications · 637 citations
5
h-index
1–5