- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This research proposes DP-LAIR, a framework for jointly protecting training data and inference-time private context in LLMs. The method combines adaptive public/private routing, latent-space Gaussian perturbation, and differentially private training of the router and decoder. Experiments on TOFU and MUSE demonstrate improved privacy-utility trade-offs compared with independently composed DP mechanisms.
Critical strengths
- The paper addresses an important and practical problem by considering both training-time and inference-time privacy within a unified framework.
- The adaptive routing mechanism and latent-space perturbation provide an interesting approach to balancing privacy protection and generation utility.
Critical weaknesses
- Unclear training-data privacy guarantee. Stage I trains the encoder and covariance using the private training corpus, therefore Stage II should only applies DP training to the router and decoder. Moreover, the private backbone is adapted using downstream data. It is unclear how the overall training-data privacy guarantee holds when these components may already contain information from the protected corpus.
- Insufficient analysis of inference overhead. The proposed LOO privacy accounting requires evaluating multiple context variants during generation but lacks of the detailed measurements of inference latency and computational cost.
- The experiments primarily rely on perplexity to measure generation utility. Additional task-level metrics, such as QA accuracy or F1, would help demonstrate whether the method preserves the ability to answer questions requiring private information
Questions for authors
- How does the training-data DP guarantee account for the Stage-I encoder, learned covariance, and downstream-adapted private backbone?
- Does the LOO-based privacy accounting introduce substantial computational overhead for longer private contexts?
Response to Reviewer Lb5t
Thanks for your question, we would like to answer your question one by one:
Response to W1 and Q1
We would like to clarify that our paper explicitly defines Infer-RDP under the API-only threat model, as emphasized in the Introduction. The adversary observes only the released API transcript, without access to model parameters, hidden states, or internal components. Crucially, Infer-RDP is defined conditional on a shared and fixed deployment state ωf, where Phase 1 outputs (e.g., the trained encoder and covariance) are treated as fixed internal components. As specified in Section 3.1 (p. 3, lines 157–159) and formalized in Lemma 3.2, the transcript distribution PSx,Sy is conditioned on this fixed state. This reflects practical API deployments, where internal components remain fixed and inaccessible to users A similar separation is adopted in Sampling and Aggregation [1], where intermediate computations need not be DP, while the released aggregate is protected by the DP mechanism. We provide a new Figure to highlight threat model difference in introduction in the revised version.
In Stage I, we non-privately train the encoder and covariance using Sx. These components, together with the private backbone, are then frozen before Stage II and treated as part of the fixed deployment state ωf. Although they remain involved in inference, their state is shared across neighboring Stage-II executions. Importantly, this assumption does not require these components to be independent of their historical training data. In Stage II, we retain the fixed Stage-I components and retrain the router and decoder using the DP-guaranteed DPDT algorithm. Conditioned on the shared fixed state ωf, this guarantee transfers to the released API transcript through post-processing, as established in Appendix A.1.
Therefore, Our training-data privacy guarantee protects the Stage-II use of Sx, conditional on the shared fixed Stage-I state, rather than its historical non-private use in Stage I. We will make this distinction more explicit in Definition 3.1 and the revised Introduction.
[1] Nissim K, Raskhodnikova S, Smith A. Smooth sensitivity and sampling in private data analysis[C]//Proceedings of the thirty-ninth annual ACM symposium on Theory of computing. 2007: 75-84.
Response to W2 and Q2
Thanks for your suggestion, The inference latency of our method depends on the number of records in the private prompt, as the LOO privacy accounting requires evaluating multiple context variants. We note that additional computational overhead is also common in differentially private next-token generation[1,2], where multiple generations or sampling operations may be required to obtain a DP-guaranteed output. Therefore, such overhead is not unique to our method. We clarify the relationship between the inference overhead and the private prompt size in the revised manuscript. In the revised version, we highlight that the inference latency depends on the size of Sy. Equation (8) highlights the privacy computation trade off: obtaining a tighter privacy bound through LOO, rather than using a looser bound based on direct clipping, comes at additional computational cost. Specifically, it requires ∣Sy∣+1 inference evaluations per token, with the overhead increasing linearly with the size of Sy.
[1] Vinod V, Pillutla K, Guha Thakurta A. Invisibleink: High-utility and low-cost text generation with differential privacy[J]. Advances in Neural Information Processing Systems, 2026, 38: 67254-67298.
[2] Thareja R, Nakov P, Vepakomma P, et al. Dp-fusion: Token-level differentially private inference for large language models[C]//International Conference on Learning Representations. 2026, 2026: 151088-151120.
Response to W3:
Thank you for your question. We choose a generative model because the output space of QA tasks is much smaller than that of text generation. In this case, directly applying the exponential mechanism to select an answer would be a more straightforward approach. Therefore, we use perplexity (PPL) to evaluate generation utility, as it is one of the most widely used metrics for differentially private text generation [1,2]. Moreover, we also provide more metrics such as PII exact match and LLM as a judge method to further evaluate the empirical privacy protection performance. Please refer to Response to Reviewer 2C98 for detailed result.
[1] Flemings J, Razaviyayn M, Annavaram M. Differentially private next-token prediction of large language models[C]//Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024: 4390-4404.
[2] Thareja R, Nakov P, Vepakomma P, et al. Dp-fusion: Token-level differentially private inference for large language models[C]//International Conference on Learning Representations. 2026, 2026: 151088-151120.