REVIEW 8 cited by
Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
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 $\textit{benign relearning attacks}$. 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. For example, we show that relearning on public medical articles can lead an unlearned LLM to output harmful knowledge about bioweapons, and relearning general wiki information about the book series Harry Potter can force the model to output verbatim memorized text. 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. Our work indicates that current approximate unlearning methods simply suppress the model outputs and fail to robustly forget target knowledge in the LLMs.
Forward citations
Cited by 8 Pith papers
-
Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration
Margin Calibration, a non-saturating margin-anchored LoRA polish, crosses the margin cliff and cuts post-attack relearn recovery on all 97 populated cells in the paper's stress matrix.
-
You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
A per-prompt cross-attention spike detector plus repulsive-attractive guidance (GUARD) substantially reduces verbatim and template memorization in Stable Diffusion at inference time.
-
Understanding Machine Unlearning Through the Lens of Mode Connectivity
Unlearned models usually connect to their originals by smooth low-loss paths, and the smoothness of that path can predict how hard the unlearning task was.
-
Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning
A bilevel meta-training method aligns text-only backbone unlearning with full vision-language model forgetting, improving forget-retain trade-offs across two VLMs and two meme datasets.
-
Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning
SFT models forget facts more stably than pretrained models, with 10-50% higher retention of unrelated knowledge when using the DUET benchmark of 28.6k Wikidata triplets.
-
Towards Evaluation for Real-World LLM Unlearning
DCUE evaluates LLM unlearning by comparing core-token confidence score distributions of the unlearned model and the original model, corrected by a validation set, using the Kolmogorov-Smirnov test.
-
Existing Large Language Model Unlearning Evaluations Are Inconclusive
Existing LLM unlearning evaluations are inconclusive: they can inject new information, depend heavily on task format, and rely on spurious correlations.
-
Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models
Step-by-step reasoning prompts can recover purportedly erased facts from unlearned LLMs, but the paper's quantitative evidence is internally inconsistent.
Discussion (0). Sign in to comment.