Layered Unlearning for Adversarial Relearning
Name
qian-tcqian-meng-eecs-2025-thesis.pdf
Description
Thesis PDF
Size
1.7 MB
Format
Adobe PDF
Checksum (MD5)
4c2a6fcb2db3f54bdb95b10c1a31584b
Author(s)
Qian, Timothy
Advisor(s)
Hadfield-Menell, Dylan
Date Issued
May 2025
Publisher
Massachusetts Institute of Technology
Abstract
Our goal is to understand how post-training methods, such as fine-tuning, alignment, and unlearning, modify language model behavior and representations. We are particularly interested in the brittle nature of these modifications that makes them easy to bypass through prompt engineering or relearning. Recent results suggest that post-training induces shallow contextdependent “circuits” that suppress specific response patterns. This could be one explanation for the brittleness of post-training. To test this hypothesis, we design an unlearning algorithm, Layered Unlearning (LU), that creates distinct inhibitory mechanisms for a growing subset of the data. By unlearning the first 𝑖 folds while retaining the remaining 𝑘 − 𝑖 at the 𝑖th of 𝑘 stages, LU limits the ability of relearning on a subset of data to recover the full dataset. We evaluate LU through a combination of synthetic and large language model (LLM) experiments. We find that LU improves robustness to adversarial relearning for several different unlearning methods. Our results contribute to the state-of-the-art of machine unlearning and provide insight into the effect of post-training updates.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
