- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper focuses on a machine unlearning method evaluation task. Machine Unlearning aims to let the model forget target domain knowledge and keep its performance on other (retain) data. Whether the effect of training data remains in the model or not is always an important question in the security domain. The authors propose a provenance audit method to address this issue. By detecting the difference between two different forget-example loss weights, this work builds a stream-matched training contrast. As shown in the experimental results, behavioral unlearning does not necessarily imply the removal of the underlying training effect.
Critical strengths
-
The motivation of this paper is clear and insightful. To test whether an unlearning method removed the effect of training on the forgotten examples or just had worse performance on these examples.
-
The proposed method is clear and easy to follow.
-
The experimental results in Section 4 are comprehensive and show that the identified exposure subspace causally influences target behavior across multiple model families and scales.
Critical weaknesses
-
The novelty of this work is not sufficient. In my view, the contribution is more of an engineering-driven improvement in characterization rather than a genuinely novel scientific insight into the mechanism.
-
There is a significant gap between the experimental setting and real-world unlearning. Can the authors propose more results under unlearning knowledge acquired during a large-scale pretraining setting?
-
Lacks formal guarantees on why this measurement can detect the remaining information in the remaining data.
-
The most important result in the abstract part (15-42%) may be over-interpreted. In my view, this is a normalized target-score margin change (Eq. 4).
-
The authors have not sufficiently demonstrated that the residual represents the truly retained influence of the data to be forgotten.
-
Several equations are not numbered, which makes them difficult to reference. The authors are encouraged to number these equations for better readability.
Questions for authors
See in Weakness.