- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes HPFL, a hybrid privacy-preserving federated learning framework that combines homomorphic encryption (HE) and differential privacy (DP). The method dynamically adjusts the HE ratio based on each client's computational and communication resources, and uses gradient magnitudes to select which model parameters should be encrypted. The authors derive an optimal HE ratio and evaluate the method on several datasets, including FMNIST, CIFAR-10, and STL-10.
Critical strengths
I think the paper addresses a practical and interesting problem, as balancing privacy, model accuracy, and computational efficiency is important in federated learning. The idea of dynamically adjusting the HE ratio based on client capabilities is reasonable, especially when clients have different computational resources. I appreciate that the authors include several datasets, ablation studies, and privacy attack evaluations to support their method.
Critical weaknesses
-
I have some concerns about the hybrid aggregation in Eq. (6). Since different clients may use different masks, it is unclear whether combining the aggregated HE and DP parameters using each client's own mask can correctly recover the global model. Some contributions from other clients seem to be missing.
-
I am not fully convinced by the privacy analysis in Appendix C. In particular, Eq. (C.1) seems to replace coordinate-wise masking with a scalar DP ratio, which is not generally equivalent. Also, the masks are selected based on local gradients, but I could not find a clear analysis of how this affects the overall privacy guarantee across multiple training rounds.
-
I find the derivation of the optimal HE ratio somewhat questionable. In Eq. (9), both terms appear to increase with the round duration, so I do not quite see why the objective should have the unique optimum claimed by the authors. I think this part needs a more careful explanation.
-
There also seems to be an issue with the mask selection in Eq. (12). If the HE ratio is used directly as the quantile threshold, selecting parameters above that threshold would generally give a fraction of approximately rather than . Unless the authors are using a different quantile definition, the selected HE ratio may not match the intended one.
Questions for authors
-
Could the authors explain how the aggregation works when clients use different masks? In particular, how does the method ensure that all clients obtain the same correctly aggregated global model?
-
Could the authors clarify the privacy guarantee for the complete framework, especially considering the gradient-based mask selection and multiple training rounds?
-
Could the authors provide more details on why Eq. (9) has a unique optimum? From the current formulation, the objective seems to be monotonically increasing.
-
Could the authors clarify the quantile definition used in Eq. (12)? How does the resulting mask ensure that the fraction of HE-protected parameters matches the optimal HE ratio?