No Time to Spare: Adversarial Machine Learning at Training and Inference Time

Abstract

This thesis addresses the critical challenge of adversarial machine learning in deep learning models, focusing on the defense mechanisms against evasion (adversarial) attacks and backdoor attacks. Part I analyzes evasion attacks through the lens of information bottleneck theory, revealing that compressing redundant information in the input space enhances model robustness. This insight leads to the proposal of novel, theoretically grounded adversarial training methods for stronger defense against

Categories

Framework mappings

Suggested from the entry's categories.

@misc{xu2026no,
  title = {{No Time to Spare: Adversarial Machine Learning at Training and Inference Time}},
  author = {Xiaoyun Xu},
  year = {2026},
  month = jan,
  doi = {10.54195/9789465152103},
  url = {https://doi.org/10.54195/9789465152103}
}