- Rating
- 3
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper introduces Recursive Self-Generation (RSG), a framework for improving membership inference attacks by repeatedly feeding a generative model’s output back as its next input. The authors observe that training samples tend to remain anchored near their original states, whereas non-members drift more rapidly toward the model’s learned distribution. They extract trajectory features and combine them with existing attack scores through an L1-regularized logistic regression classifier. Experiments across diffusion models, image autoregressive models, Transformers, and state-space language models show improved TPR at 1% FPR in 118 of 122 attack–model combinations, suggesting that recursive trajectories contain membership information missed by single-query attacks. However, the method requires labeled member and non-member data for calibration, incurs multiple generation queries, and sometimes reduces AUROC on LLMs, indicating that its gains are concentrated in the low-FPR region rather than reflecting uniformly better membership discrimination.
Critical strengths
The anchored-versus-drifting phenomenon identified in this paper is both novel and conceptually compelling. The experiments demonstrate that recursive self-generation trajectories provide substantial membership signals beyond those captured by existing attacks, particularly in the low-FPR regime. Most notably, the phenomenon is consistently observed across different modalities and model families. This cross-modal and cross-architectural generality significantly strengthens the paper’s contribution and suggests that the proposed phenomenon may reflect a broadly shared property of generative models. More broadly, this finding opens up a promising new perspective on memorization in generative models and is likely to inspire substantial follow-up work on privacy auditing, membership inference, and generative-model dynamics.
Critical weaknesses
-
The method requires labeled calibration data. It trains a logistic regression classifier using known members and non-members. However, in a realistic MIA setting, the attacker may not know which samples were used to train the target model. The paper should clarify where these labels come from and test whether the method works without target-specific labeled data.
-
AUROC decreases on some LLMs. The method improves TPR at 1% FPR, but Table 13 shows lower AUROC for several attacks. Low-FPR performance is important, but AUROC still measures the attack’s overall ability to separate members from non-members. The paper should explain this trade-off and show more complete results, such as ROC curves and partial AUC.
Questions for authors
Where do the labeled member and non-member samples used to train the logistic regression classifier come from? Can the method still work without target-specific labeled data?
Why does the method improve TPR at 1% FPR but reduce AUROC for several LLM attacks? Could you provide full ROC curves or partial AUC results to explain this trade-off?
3 comments
I understand that member and non-member labels are needed to evaluate attack performance. My concern is that your method also uses known members of the target model to train the attack classifier. This is a separate requirement: an evaluator can use ground-truth labels to measure performance, while an attacker may not have access to confirmed members of the target model’s training set. The held-out evaluation does not address the practical availability of this calibration data. Could you clarify which realistic attack scenarios provide such known members, and test whether the gains persist when the classifier is calibrated on an auxiliary model without using target-specific membership labels?
Answer
Sorry for the misunderstanding. Even established MIAs use some calibration data. From the Min-K++ paper: "The authors of Min-K% were using validation data to determine the hyperparameter k, yet the validation data is not released. For this reason, we choose to sweep over 10, 20, ..., 100 and report the best result for both Min-K% and Min-K%++ for fair comparison". CAMIA also uses calibration data to fit LR.
But our approach's gains stay even under the more practical setup:
Assume an auditor has (i) the target data X whose membership is in question (unlabelled) and (ii) a set N of known non-members (the established assumption of MIAs). We replace the LR with an LDA estimated from X and N alone. The approach therefore needs nothing beyond the standard MIA calibration assumption. Results (TPR@1%FPR):
| Model, attack | Base | +ours, LDA | +ours, LR |
|---|---|---|---|
| VAR-30, Loss | 4.0 | 6.4 | 6.6 |
| VAR-30, Min-K% | 8.4 | 12.5 | 12.7 |
| RAR-XXL, Loss | 6.0 | 9.2 | 9.4 |
| RAR-XXL, Min-K% | 10.9 | 13.1 | 14.5 |
| DiT-XL, PIA | 2.8 | 25.3 | 21.2 |
| DiT-XL, Denoising loss | 1.3 | 26.0 | 27.4 |
Without any member labels, the LDA variant recovers all of the LR gain or even beats it.
We hope this clarification adequately addresses the reviewer's concern.
Rebuttal
We sincerely thank the reviewer for their time and feedback.
W1: This is the standard protocol, not an additional assumption. Examples of established works that use the same procedure are LiRA [1], CDI [2], and MIA for IARs [3].
Q1: The labels come from the benchmark’s own ground-truth split, which is what makes evaluation possible at all: ImageNet and COCO train/test splits for vision models, and MIMIR’s member/non-member sets for LLMs. Concretely, we draw repeated stratified train/test splits, fit the L1-regularized logistic regression on the training half of each, evaluate on the held-out half, and aggregate scores across splits. This is the standard protocol in the MIA literature [1], [2].
W2/Q2: The two metrics measure different regions of the ROC curve, and our features act on one of them. Trajectory features sharpen the high-confidence tail, where a positive call can be acted on, while contributing little or occasionally costing in the mid-FPR regime that dominates AUROC. Following [1], we judge attacks by TPR@1%FPR rather than AUC, because AUC averages over the high-FPR regime where no audit would operate, so a method that improves confident detections while losing marginally in aggregate ranking is nonetheless the stronger attack. Also, Table 13 shows the effect on AUC is small and two-sided.
We hope our responses adequately address the concerns and appreciate your consideration of these clarifications in your final assessment.
[1] Carlini et al. Membership Inference Attacks From First Principles, 2022
[2] Dubiński et al. CDI: Copyrighted Data Identification in Diffusion Models, 2025
[3] Kowalczuk et al. Privacy Attacks on Image AutoRegressive Models, 2025