Science Explorer Back to mapMap
Discussion
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. 9.8% 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%
1.9k
per year above
Top-10% rate
9.8%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+152%
the tick is no change
Largest producer
China
39% of the 10 largest, 2022-now
Adversarial Robustness in Machine Learning

Which countries lead Adversarial Robustness in Machine Learning research?

By volume, China and the United States publish the most (4.2k and 2.7k works in 2022-now).

By volume, 2022-now

  1. 1 China 4.2k works
  2. 2 United States 2.7k works
  3. 3 India 1.1k works
  4. 4 Germany 535 works
  5. 5 United Kingdom 529 works
  6. 6 South Korea 357 works
  7. 7 Canada 340 works
  8. 8 Australia 324 works
  9. 9 Italy 318 works
  10. 10 Japan 281 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: 39.3%United States: 25.4%India: 10.4%Germany: 5.0%6 others listed: 20.0%39%largest
China4,219 · 39.3%United States2,726 · 25.4%India1,117 · 10.4%Germany535 · 5.0%6 others listed2,149 · 20.0%

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

Which institutions lead Adversarial Robustness in Machine Learning research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Adversarial Robustness in Machine Learning research, followed by National University of Defense Technology and Shanghai Jiao Tong University.

By volume, 2022-now

  1. 1 Chinese Academy of SciencesChina 190 works
  2. 2 National University of Defense TechnologyChina 102 works
  3. 3 Shanghai Jiao Tong UniversityChina 88 works
  4. 4 Tsinghua UniversityChina 86 works
  5. 5 Xidian UniversityChina 82 works
  6. 6 Nanyang Technological UniversitySingapore 82 works
  7. 7 Zhejiang UniversityChina 79 works
  8. 8 Beihang UniversityChina 76 works
  9. 9 University of Electronic Science and Technology of ChinaChina 73 works
  10. 10 Beijing University of Posts and TelecommunicationsChina 72 works

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

The most-cited researchers publishing on Adversarial Robustness in Machine Learning include Kaiming He, Yoshua Bengio and Geoffrey E. Hinton.

  1. 1 Kaiming He Israel 562k citations
  2. 2 Yoshua Bengio Canada 476k citations
  3. 3 Geoffrey E. Hinton Canada 454k citations
  4. 4 Shaoqing Ren China 356k citations
  5. 5 Ross Girshick Israel 356k citations
  6. 6 Xiangyu Zhang 327k citations
  7. 7 Karl John Friston United Kingdom 310k citations
  8. 8 Jian Sun 281k citations
  9. 9 Xiaogang Wang China 260k citations
  10. 10 Yann LeCun United States 256k citations

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

What are the most cited papers in Adversarial Robustness in Machine Learning?

The most cited paper in Adversarial Robustness in Machine Learning is "Rethinking the Inception Architecture for Computer Vision" (Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe et al., 2016), with 31,624 citations. Next come "MobileNetV2: Inverted Residuals and Linear Bottlenecks" (26,808) and "CBAM: Convolutional Block Attention Module" (23,707).

Most cited papers
#PaperReleasedCitations
1 Rethinking the Inception Architecture for Computer Vision Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe et al. Conference paper Jun 2016 31,624
2 MobileNetV2: Inverted Residuals and Linear Bottlenecks Mark Sandler, Andrew Howard, Menglong Zhu et al. Conference paper Jun 2018 26,808
3 CBAM: Convolutional Block Attention Module Sanghyun Woo, Jongchan Park, Joon‐Young Lee et al. · Lecture notes in computer science Conference paper 2018 23,707
4 An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov et al. · arXiv (Cornell University) PreprintOpen access 22 Oct 2020 22,044
5 Xception: Deep Learning with Depthwise Separable Convolutions François Chollet Conference paper Jul 2017 19,596
All 98 most cited papers, with filters and sorting

Where is Adversarial Robustness in Machine Learning research done?

The largest centres of Adversarial Robustness in Machine Learning research in 2022-now are Beijing (China), Shanghai (China), Nanjing (China) and Xi'an (China). Among places with at least 20 works in it, it is an unusually large share of all research in Saarbrücken.

Largest cities, 2022-now

  1. 1 BeijingChina 882 works
  2. 2 ShanghaiChina 343 works
  3. 3 NanjingChina 280 works
  4. 4 Xi'anChina 235 works
  5. 5 GuangzhouChina 203 works
  6. 6 SingaporeSingapore 198 works
  7. 7 HangzhouChina 197 works
  8. 8 SeoulSouth Korea 193 works
  9. 9 WuhanChina 185 works
  10. 10 ChangshaChina 159 works

Where it is the local speciality

  1. SaarbrückenDE · 35.0 works7.9×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Adversarial Robustness in Machine Learning than the world average.

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, Hong Kong University of Science and Technology and Tsinghua University 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%10%20%mean 15.92%fractional works in this field (log) →share of work in the world top 10% →Hong Kong University…Nanyang Technologica…Tsinghua UniversityXidian University
above the meannear itbelow it

One dot per university in the first ten of the table below, at the default weights. The upper left is the interesting corner: small places doing unusually strong work.

Excellenceshare of its work in the world top 10%, 2022-now and all time averaged
40%
Specialisationhow much of its work is in this field, counted up to 10× the world share
10%
Sizeits output in this field, on a log scale
30%
Growthoutput growth, counted from -20% to +20%
10%
Internationalshare of its work with a co-author abroad
10%
Each slider sets a weight; the share it gets of the score is beside it.
#UniversityScoreTop 10%SpecialisationWorksGrowth
1Nanyang Technological UniversitySingapore 75.117.4%8.9×82 +122.8%
2Hong Kong University of Science and TechnologyChina 71.022.0%6.5×31 +427.3%
3Tsinghua UniversityChina 65.013.6%3.2×86 +40.7%
4Xidian UniversityChina 64.713.3%9.8×82 +464.5%
5Beihang UniversityChina 64.514.3%6.0×76 +240.5%
6Xi'an Jiaotong UniversityChina 62.319.0%2.6×52 +272.4%
7Zhejiang UniversityChina 61.813.3%2.5×79 +259.5%
8University of Technology SydneyAustralia 61.216.1%6.7×34 +161.1%
9Wuhan UniversityChina 60.512.0%4.4×72 +358.2%
10Singapore Management UniversitySingapore 60.518.2%18.4×23 +280.2%

Universities only. The score blends excellence (40%), size (30%), specialisation (10%), growth (10%), international reach (10%), 2022-now; growth compares 2018-21 with 2022-25 and counts up to +20%, since a jump from a small base is mostly noise.

Every institution in Adversarial Robustness in Machine Learning, country by country

Is Adversarial Robustness in Machine Learning research growing?

Output in 2022-2025 was 152% higher than in 2018-2021, peaking in 2025. The fastest-growing topics are Adversarial Robustness in Machine Learning.

still counting19801990200020102020
grewheldshrank

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

Its share of all research

Growing output can still be a shrinking share: all of science grows. This is Adversarial Robustness in Machine Learning as a percentage of every work published that year, 0.044% in 2024.

still counting0.025%0.050%0.075%Adversarial Robustness in Machine Learning0.064% in 202519801990200020102020

Fractional works of Adversarial Robustness in Machine Learning over all fractional works that year. How the balance of science has shifted.

How much of it reaches the world top 10%

Year by year.

still counting5%10%15%Adversarial Robustness in Machine Learning9.7% in 20252020

Of each year's works in it, the share that reached the world's 10% most cited for their field and year. A field is the world for its own topics, so there is no other line to hold it against.

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.

Discussion

Ask a question or share a note about Adversarial Robustness in Machine Learning. Posts are plain text and can be reported.