Theory of Continual Learning Against Data Poisoning Attacks

Abstract

Continual learning (CL), where a model is trained on a sequence of data tasks, is increasingly being adopted across key fields such as large language models and image recognition, yet it remains highly vulnerable to data poisoning that triggers learning divergence or severe excess risk. Despite these threats, a principled theoretical foundation in CL for understanding attack and defense remains lacking. In this paper, we develop a theoretical framework to analyze strategic attacks and defenses i

Categories

Framework mappings

Suggested from the entry's categories.

@misc{hu2026theory,
  title = {{Theory of Continual Learning Against Data Poisoning Attacks}},
  author = {Yiting Hu and Lingjie Duan},
  year = {2026},
  month = jun,
  eprint = {2606.29841},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.29841}
}