AI Security Research Should Better Incentivize Defense Research

Abstract

This work examines an imbalance in artificial intelligence (AI) security research: the field tends to produce more work on attacking AI systems than on defending them. Drawing on related academic papers, we find biased attack-to-defense ratios across subfields, including federated learning, speech recognition, membership inference, large language models, etc. The imbalance possibly means far beyond a simple count: attack papers are routinely evaluated under favorable conditions that make threats

Categories

Framework mappings

Suggested from the entry's categories.

@misc{zhang2026ai,
  title = {{AI Security Research Should Better Incentivize Defense Research}},
  author = {Youqian Zhang},
  year = {2026},
  month = may,
  eprint = {2605.23448},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.23448}
}