Science Explorer Interactive view Map
Topic · Artificial Intelligence

Adversarial Robustness in Machine Learning

Adversarial Robustness in Machine Learning is a research topic within Artificial Intelligence. Science Explorer counts 19k research works in it since 1964. 22.4% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on the robustness of deep learning models against adversarial attacks, exploring topics such as adversarial examples, security, uncertainty estimation, defenses, and verification. It delves into the challenges and potential solutions for ensuring the resilience of neural networks in the face of malicious inputs.

  • Adversarial Examples
  • Deep Learning
  • Robustness
  • Neural Networks
  • Machine Learning
  • Security
  • Uncertainty Estimation
  • Defenses
  • Attack
  • Verification
Research works
19k
fractional, since 1964
In the world top 10%
4.3k
per year above
Top-10% rate
22.4%
share of its works in the world top 10%
Growth, 2013–17 → 2018–22
+1032%
the tick is no change

Which countries lead Adversarial Robustness in Machine Learning research?

By volume, China and the United States publish the most (3.2k and 2k works in 2022–2025).

By volume, 2022–2025

  1. 1 China 3.2k works
  2. 2 United States 2k works
  3. 3 India 760 works
  4. 4 Germany 442 works
  5. 5 United Kingdom 406 works
  6. 6 South Korea 283 works
  7. 7 Australia 272 works
  8. 8 Canada 267 works
  9. 9 Italy 263 works
  10. 10 Japan 236 works

How concentrated that is

The same countries as shares of everything the list above accounts for. A node where two countries do two thirds of the work and one spread evenly across twelve read alike as a ranking and not at all alike here.

China: 39.2%United States: 24.9%India: 9.3%Germany: 5.4%6 others listed: 21.2%39%largest
China3,196 · 39.2%United States2,030 · 24.9%India760 · 9.3%Germany442 · 5.4%6 others listed1,727 · 21.2%

Shares of the rows listed above, not of the whole node.

Which institutions lead Adversarial Robustness in Machine Learning research?

By volume in 2022–2025, National University of Defense Technology publishes the most Adversarial Robustness in Machine Learning research, followed by Tsinghua University and Shanghai Jiao Tong University.

By volume, 2022–2025

  1. 1 National University of Defense TechnologyChina 83 works
  2. 2 Tsinghua UniversityChina 71 works
  3. 3 Shanghai Jiao Tong UniversityChina 71 works
  4. 4 Xidian UniversityChina 67 works
  5. 5 Nanyang Technological UniversitySingapore 64 works
  6. 6 Chinese Academy of SciencesChina 62 works
  7. 7 Zhejiang UniversityChina 61 works
  8. 8 Wuhan UniversityChina 60 works
  9. 9 University of Electronic Science and Technology of ChinaChina 60 works
  10. 10 Beihang UniversityChina 60 works

Who are the leading researchers in Adversarial Robustness in Machine Learning?

The most-cited researchers publishing on Adversarial Robustness in Machine Learning include Li Fei-Fei, Yoshua Bengio and Serge Belongie.

  1. 1 Li Fei-Fei United States 17k citations
  2. 2 Yoshua Bengio Canada 17k citations
  3. 3 Serge Belongie United States 14k citations
  4. 4 Olga Russakovsky United States 8.9k citations

Ranked by citations received across their whole record, among researchers with at least three works on this topic.

Where is Adversarial Robustness in Machine Learning research done?

The largest centres of Adversarial Robustness in Machine Learning research in 2022–2025 are Beijing (China), Shanghai (China), Nanjing (China) and Xi'an (China).

Largest cities, 2022–2025

  1. 1 Beijing China 714 works
  2. 2 Shanghai China 281 works
  3. 3 Nanjing China 229 works
  4. 4 Xi'an China 189 works
  5. 5 Hangzhou China 162 works
  6. 6 Singapore Singapore 157 works
  7. 7 Guangzhou China 155 works
  8. 8 Seoul South Korea 153 works
  9. 9 Wuhan China 150 works
  10. 10 Changsha China 126 works
See Adversarial Robustness in Machine Learning on the map

Where is the best place to study Adversarial Robustness in Machine Learning?

Among universities, judged by research, Nanyang Technological University, Carnegie Mellon University and Singapore University of Technology and Design score highest, combining excellence, specialisation, size, growth and international reach. Research strength is one signal when choosing where to study; it does not measure teaching.

0%20%40%mean 32.72%fractional works in this node (log) →share in the world top 10% →Nanyang Technological University: 64, 31.8%Carnegie Mellon University: 34, 28.2%Singapore University of Technology and Design: 9, 45.1%Singapore Management University: 18, 35.5%City University of Macau: 14, 38.6%Mohamed bin Zayed University of Artificial Intelligence: 10, 35.8%Xidian University: 66, 27.3%Hong Kong University of Science and Technology: 26, 35.5%National University of Defense Technology: 83, 14.7%University of Technology Sydney: 29, 34.7%Singapore University…Singapore Management…Nanyang Technologica…Carnegie Mellon Univ…
above the meannear itbelow it

One dot per university in the table below. The upper left is the interesting corner: small places doing unusually strong work.

#UniversityScoreTop 10%SpecialisationWorksGrowth
1 Nanyang Technological UniversitySingapore 77.831.8%8.0×64 +409.0%
2 Carnegie Mellon UniversityUnited States 66.328.2%8.3×34 +659.0%
3 Singapore University of Technology and DesignSingapore 64.845.1%9.6×9 —
4 Singapore Management UniversitySingapore 64.735.5%16.5×18 —
5 City University of MacauMacau 63.638.6%8.9×14 —
6 Mohamed bin Zayed University of Artificial IntelligenceUnited Arab Emirates 63.335.8%24.2×10 —
7 Xidian UniversityChina 63.227.3%9.0×66 —
8 Hong Kong University of Science and TechnologyHong Kong 61.235.5%6.8×26 —
9 National University of Defense TechnologyChina 58.814.7%10.7×83 —
10 University of Technology SydneyAustralia 58.434.7%6.5×29 —

Universities only. Score blends excellence (30%), specialisation (25%), size (20%), growth (15%) and international reach (10%), 2015–2022; growth compares 2010–14 with 2015–19.

Is Adversarial Robustness in Machine Learning research growing?

Output in 2018–2022 was 1032% higher than in 2013–2017, peaking in 2025. The fastest-growing topics are Adversarial Robustness in Machine Learning.

19801990200020102020
grewheldshrank

The same series as a ribbon — one cell per year, darker for more. The line above answers how much; this answers when.

Which topics inside it are moving

Growth and decline on one axis around a shared zero. Two lists side by side hide the thing that matters: whether the growth dwarfs the decline, or the other way round.