- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper proposes QF-Entanglement, a representation-based method for class unlearning that aims to avoid the statistical artifacts caused by aggressive loss maximization. It identifies an active feature subspace from forget–retain discrepancies, moves forget representations toward a nearby retain-class centroid, and matches their linear entropy while preserving the orthogonal complement and training on retained data. The analysis provides a conditional utility bound and relates entropy matching to effective-rank preservation. Experiments use ResNet-18 across five image-classification datasets, with evaluations of forgetting, retained accuracy, membership inference, and representation similarity to retrained models. The reported results suggest a favorable privacy–utility trade-off against the evaluated baselines.
Critical strengths
The method addresses a meaningful limitation of loss-maximization approaches: suppressing forget accuracy can create statistical artifacts without reproducing the behavior of a retrained model. Combining targeted representation changes with preservation of shared features is a reasonable approach to balancing forgetting and retained utility.
The experiments include retrained references, membership inference at low false-positive rates, and representation probes alongside classification accuracy. The reported results, particularly on CIFAR-100, provide encouraging evidence that the method can suppress the forgotten class while preserving utility and approaching retrained behavior on several measures.
Critical weaknesses
The proposed alignment target is not sufficiently justified as a proxy for unlearning. A model retrained without the forget class need not map its samples to a single neighboring retain-class distribution. Matching that class’s centroid and linear entropy may suppress the original classification behavior while preserving information about the forgotten data. The paper does not establish why this target should reproduce retrained behavior, and matching a scalar entropy statistic is insufficient to support its broader claims of distributional indistinguishability and protection against membership inference.
The contribution over existing representation-based methods remains unclear. DUCK already moves forget embeddings toward nearby incorrect class centroids, while MUDA aligns forget representations with the retain feature space. Neither is included in the comparisons, although both directly relate to the paper’s central idea. Comparisons with POUR and TRW, together with the neighboring-class attack MIA-NN, are also missing. Without these comparisons, it is difficult to determine whether the proposed combination provides a meaningful improvement over existing alignment methods or avoids the privacy leakage that motivates the paper.
Questions for authors
Clarification requests:
- What evidence supports using a neighboring retain class as the target distribution for forgotten samples? Which classes are selected in the reported experiments, and how closely does this alignment reproduce the representations and predictions of models retrained without ?
- Linear entropy is invariant to covariance scaling, so matching it does not control total variance or guarantee a nonsingular covariance. What additional assumptions justify Corollary 1’s conclusions about likelihood anomalies and membership inference?
Additional evidence needed to assess the current claims:
- How does the method compare with DUCK and MUDA, which already use centroid movement or representation alignment, and with POUR and TRW? These comparisons would help establish the contribution of the proposed combination.
- Does the reported privacy improvement persist under MIA-NN or another attack that examines predictions on neighboring retained classes? This is particularly relevant because the method explicitly redirects forgotten representations toward such classes.
Response to Reviewer DBGs
We thank Reviewer DBGs for highlighting key representation-level baselines and neighbor-aware audits.
W1 & Clarification Q1, Q2. Alignment Target and Variance Control
W2 & Additional Evidence Q1. Comparison with DUCK, MUDA, POUR, and TRW
All four representation-level baselines were evaluated on CIFAR-100 (seed 42; Appendix B.8, Table 17):
Table R3: CIFAR-100 Representation Unlearning Baselines (Seed 42)
DUCK and TRW leave residual forget accuracy (1.40%) and degrade retain test utility (68.00%, 70.88%); MUDA shows higher MIA deviation (53.00%); QF-Entanglement achieves complete erasure (0.00%), exact chance MIA (50.00%), and retain test utility (75.79%) closest to Retrain (76.47%).
Additional Evidence Q2. Resistance Under MIA-NN
Evaluations under MIA-NN on CIFAR-10 (Appendix B.7, Table 15) confirm that neighbor-class alignment introduces no detectable prediction signature:
Table R4: CIFAR-10 MIA-NN Target Attack Evaluation
Revision: Added Tables 14, 15, and 17 in Appendix B.7–B.8 and updated the Bibliography.
We hope these baseline comparisons and neighbor-aware audits address your questions, and we would deeply appreciate your consideration of a higher score.
References: