- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduce an interesting defense against attacking a split inference settings. The defense learns a weights perturbation that keeps the necessary information such that the server can still predict while making it harder for the attack to gather enough information about the training set to train its own model. The defense only perturbs the client's weights so no server retraining is needed. The authors showed empirically that the learned perturbations only have a small degradation on the server accuracy while having a large degradation on the attacker's model.
Critical strengths
- The paper introduces a defense that does not need to retrain the server, only the client. This makes the defense practical.
- Using weights perturbations is a nice way of defending, and to the best of my knowledge is the first defense to use it for against privacy attacks.
Critical weaknesses
-
The experiments are quite limited. The network are only ResNet20, VGG11-BN, MobileNetV2. There are not Transformer based networks. In addition, the datasets are very simple and it is not obvious if the defense holds in the real world settings.
-
The benchmark is against old attacks. It would be interesting to add PCAT (Gao & Zhang, USENIX Security 2023)
-
To my understanding, Figure 2 shows reconstructed input from the attack. To me it seems very similar to the original input which may suggest that the defense does not protect from classic reconstruction attack. It would be nice to add image similarity metrics such as SSIM or LPIPS to validate the scope of the defense to reconstruction attacks.
Questions for authors
- Does the defense work on other scopes than images? for example text classification (GLUE, IMDb)
- Is the code available to reproduce the experiments?
2 comments
I thank the authors for their response. I feel like the contribution of the paper is limited. The paper is empirical, and propose an actual defense that should work in the real world. The paper does not cover modern architectures and split attacks, and it seems that even the current experiment present a very narrow defense against a specific attack while showing that the defense does not work for the more dangerous, reconstruction attack.
I believe the paper would benefit if it shows that the defense is more robust, either to other types of attack, or even to more modern split attacks.
I would maintain my current score.
Response to Reviewer K9km: Evaluation Coverage, Reconstruction Metrics, and Reproducibility
Thank you for recognizing the practical value of preserving the server model and the interest of learning client-side weight perturbations. We appreciate your suggestions and clarify the scope of the current evidence below.
1. Architectures and datasets. The evaluation distinguishes the protected model from downstream evaluators. ResNet20 is the victim, while ResNet20, VGG11-BN, and MobileNetV2 test reconstructed-data utility across classifier architectures. This checks whether the observed effect is specific to one evaluator. The datasets cover natural images and industrial surface defects through NEU-CLS, providing evidence beyond a single visual domain. These controlled experiments support the reported settings. Transformer victims and larger-scale deployment distributions would provide complementary evidence; defense effectiveness in those settings is not established by the current evaluation.
2. Additional attacks, including PCAT. We appreciate PCAT as a relevant additional attack. Our evaluation examines a freshly retrained decoder and a clean-map input-optimization procedure. The decoder is trained after defense selection using features from the selected perturbed client, so evaluation is not limited to the defense-training surrogate. Input optimization provides a distinct but restricted reconstruction setting. PCAT is not included, and our conclusions concern the evaluated procedures rather than comprehensive resistance to every reconstruction or model-stealing attack.
3. Visual similarity, SSIM, and LPIPS. Visual recognizability and downstream training utility measure different properties. A sample may remain recognizable to a human without preserving the consistency required to serve as effective training data. We quantitatively test the latter by training evaluators on reconstructed images and testing them on real held-out data. Visible similarity therefore does not by itself contradict a measured trainability reduction.
Conversely, reduced trainability does not imply that recognizable or sensitive content has disappeared. MSE is reported as a pixel-level diagnostic; SSIM and LPIPS would characterize additional structural and perceptual aspects but are not reported here. Figure 2 should illustrate reconstruction changes rather than establish visual confidentiality. Our central evidence concerns the usefulness of reconstructed datasets for downstream learning.
4. Text tasks. We have also conducted preliminary experiments on text tasks and observed encouraging initial results, suggesting potential for extending the approach beyond image classification. The mechanism modifies model parameters rather than image pixels, although text requires different reconstruction procedures and task-specific utility criteria. These experiments are time-consuming, and the current results remain exploratory rather than a comprehensive evaluation. We therefore regard them as preliminary evidence of broader applicability, while the conclusions supported by the reported systematic evaluation remain focused on images.
5. Code availability. The implementation exists in our experimental suite and includes defense training, reconstruction, data partitioning, and downstream trainability evaluation. We plan to open-source the implementation and experimental configurations after refining the manuscript and completing the supplementary experiments. This release will support independent reproduction and further investigation of the proposed approach.