1. 31,705
   adversarial machine learning articles were released between 2019 and 2024 (estd.)

   Count includes English-language articles classified under adversarial machine learning in ETO's Merged Academic Corpus. Read more >>
2. 145%
   growth in research between 2019 and 2024

   The number of English-language adversarial machine learning articles grew 145% between 2019 and 2024.
3. 2%
   of all artificial intelligence articles focused on adversarial machine learning

Yearly global adversarial machine learning research

1. 24
   citations for the average adversarial machine learning article
2. 19
   citations for the average artificial intelligence article

• Attention-Aware Discrimination for MR-to-CT Image Translation Using Cycle-Consistent Generative Adversarial Networks.
  2020: Radiology: Artificial Intelligence. 18,555 citations
• A survey on Image Data Augmentation for Deep Learning
  2019: Journal of Big Data. 13,644 citations
• BERTScore: Evaluating Text Generation with BERT
  2019: arXiv. 8,784 citations
• Deep Leakage from Gradients
  2019: arXiv. 3,077 citations
• Certified Adversarial Robustness via Randomized Smoothing
  2019: arXiv. 2,504 citations
• Training Generative Adversarial Networks with Limited Data
  2020: arXiv. 2,314 citations
• Natural Adversarial Examples
  2019: arXiv. 2,059 citations
• Alias-Free Generative Adversarial Networks
  2021: arXiv. 2,057 citations
• Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
  2019: IEEE Symposium on Security and Privacy. 2,005 citations
• Jailbroken: How Does LLM Safety Training Fail?
  2023: arXiv. 1,856 citations