RULER: Representation-Level Verification of Machine Unlearning
Machine unlearning verification typically focuses on output-level metrics, but a model can pass these while still encoding forgotten data in its internal representations. This paper introduces RULER, a set of representation-level verification metrics, including oracle-comparative M2 and oracle-free M4. Experiments show that approximate unlearning methods pass output-level tests but exhibit significant residuals in representation-level analysis.
Article intelligence
Key points
- Current output-level verification for machine unlearning is insufficient as models may retain forgotten data in intermediate representations.
- RULER introduces two representation-level metrics: M2 (requires oracle model) and M4 (oracle-free).
- Multiple approximate unlearning methods fail representation-level verification despite passing output-level evaluations.
- M4 serves as a pre-unlearning diagnostic for memorization in various domains.
Why it matters
This matters because current output-level verification for machine unlearning is insufficient as models may retain forgotten data in intermediate representations.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.27569] RULER: Representation-Level Verification of Machine Unlearning
[Submitted on 26 May 2026]
Title:RULER: Representation-Level Verification of Machine Unlearning
View a PDF of the paper titled RULER: Representation-Level Verification of Machine Unlearning, by Georgina Cosma and Axel Finke
View PDF HTML (experimental)
Abstract:Machine unlearning aims to remove the influence of specific training records from a deployed model without retraining from scratch. Current protocols verify this at the output level through membership inference, retain accuracy, and forget-set accuracy, but a model can satisfy all three whilst still encoding forgotten records in its intermediate representations. We introduce RULER, a set of representation-level verification metrics. The oracle-comparative metric M2 measures whether forget-set records occupy the same representational position as in a model retrained without them. The oracle-free metric M4 detects residuals from the unlearned model's internal similarity structure alone, without retraining. Four approximate unlearning methods all pass output-level evaluation, yet under a linear mixed-effects model M2 detects significant residuals in 10 of 12 conditions (p
new | recent | 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)