- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies contextual privacy preservation in federated settings where clients differ in their disclosure norms and the LLM backbones used by their agents. The authors propose Federated Contextual Disclosure Control (FCDC), which combines a shared contextual encoder with client-specific norm decision modules. Through nested alternating optimization, FCDC adapts local decision modules to client-specific norms while collaboratively learning shared representations. Experiments on synthetic contextual integrity data and agent privacy benchmarks demonstrate improved disclosure classification, generalization to unseen agent backbones, and better privacy–utility trade-offs compared to existing baselines.
Critical strengths
-
The consideration of both disclosure norm heterogeneity and main-agent heterogeneity provides an interesting perspective on collaborative privacy learning.
-
The paper compares FCDC against several federated learning baselines and existing privacy protection methods. It also evaluates generalization to unseen LLM backbones and considers both privacy leakage and task utility in agent interactions, providing evidence of the proposed method's effectiveness.
Critical weaknesses
-
Definition of norm heterogeneity: relation to Contextual integrity? The relationship between norm heterogeneity and contextual integrity could be clarified. The first paragraph of the Introduction motivates contextual integrity through context-dependent disclosure norms, while the second paragraph introduces norm heterogeneity as differences in disclosure conditions, such as recipient verification and consent requirements. A clearer transition between them could clarify how norm heterogeneity arises from contextual integrity.
-
Definition norm heterogeneity: explicit or implicit norm? Appendix B.1 constructs norm heterogeneity using three predefined policy variants (contextual minimum, verified recipient, and explicit consent), which appear to represent different explicit disclosure requirements rather than implicit variations in contextual norms. Is norm heterogeneity intended to capture differences in contextual privacy expectations across clients, or differences in explicitly specified disclosure policies?
-
Practical relevance of norm heterogeneity. It is unclear how the norm heterogeneity maps onto realistic deployment scenarios. Could the author provide real-world examples?
-
The proposed nested learning formulation is inspired by FedRep, which optimizes shared representations through alternating local predictor adaptation and representation updates. A comparison or clarification of technical modifications would further strengthen the work.
Questions for authors
- Could the authors clarify how norm heterogeneity relates to contextual integrity? In particular, does the proposed formulation aim to capture differences in contextual privacy expectations across clients, or differences in explicitly specified disclosure policies? How do the three predefined policy variants in Appendix B.1 reflect the broader notion of contextual norms?
- Could the authors provide a concrete real-world deployment scenario illustrating how client-specific norm heterogeneity arises in practice? In such a scenario, why would clients need to learn separate norm decision modules rather than relying on a shared policy-conditioned model?
- What technical modifications are required to adapt FedRep's alternating local predictor and shared representation learning to the proposed contextual integrity setting?