Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic Perspective

Abstract

Neuro-Symbolic (NeSy) AI has recently emerged as a novel paradigm to enable trustworthy AI, aiming at integrating sub-symbolic neural perception with grounded symbolic reasoning. The neuro-symbolic integration process that characterizes these models has been proven beneficial to achieve more transparent, explainable and efficient AI systems. Meanwhile, their properties under adversarial settings have been overlooked being frequently deemed robust-by-design. However, the neural-symbolic integrati

Categories

Framework mappings

Suggested from the entry's categories.

@misc{corallo2026does,
  title = {{Does Reasoning Mitigate Backdoor Attacks? A Neuro-Symbolic Perspective}},
  author = {Marco Antonio Corallo and Andrea Agiollo and Mauro Conti and Alberto Giaretta},
  year = {2026},
  month = sep,
  eprint = {2609.00464},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.00464}
}