Goto

Collaborating Authors

 targeted relearning attack

Jogging the Memory of Unlearned Model Through Targeted Relearning Attack

Hu, Shengyuan, Fu, Yiwei, Wu, Zhiwei Steven, Smith, Virginia

arXiv.org Artificial Intelligence

Machine unlearning is a promising approach to mitigate undesirable memorization of training data in ML models. However, in this work we show that existing approaches for unlearning in LLMs are surprisingly susceptible to a simple set of targeted relearning attacks. With access to only a small and potentially loosely related set of data, we find that we can 'jog' the memory of unlearned models to reverse the effects of unlearning. We formalize this unlearning-relearning pipeline, explore the attack across three popular unlearning benchmarks, and discuss future directions and guidelines that result from our study.

  information, knowledge, targeted relearning attack, (12 more...)
2406.13356
  Country:
  Genre:
  Industry:
  Technology:

Add feedback