- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3(+1)
Read review
Paper summary
The paper observes that text-free LLM inference, which sends perturbed embeddings instead of plaintext prompts, still leaks private content on the output path when responses must reproduce input strings such as medical terms, identifiers, or tool-call arguments. The proposed CRG keeps PPFT-style pooled and noise-perturbed inputs, but trains the server decoder to emit request-local reference tokens for input-derived content, which only the client resolves to plaintext. Across 13 benchmarks and four reconstruction attacks, CRG improves utility over PPFT, most clearly on tasks requiring exact reuse (SealTools call EM from 57.3% to 79.9%), while reducing output-side leakage.
Critical strengths
-
The problem is real and well motivated: output-side leakage of input-derived content is a genuine gap in prior input-only protection.
-
The reference mechanism is a clean technical contribution, since the decoder must learn to point to source positions without ever seeing the plaintext source tokens.
-
The privacy evaluation is thorough, covering input, joint, output-only, and raw-logit attacks plus a prompt-injection stress test in which PPFT leaks 95% of ages while CRG stays below 1%.
Critical weaknesses
-
The contribution is narrower than the framing suggests. The input side (client encoder, k-pooling, Laplace noise, continuous-input decoder) is inherited directly from PPFT, so the novelty lies only in the output-side reference mechanism.
-
The baselines miss the closest prior work on output protection. HaS and PrivacyRestore, whose placeholder-and-restore design is conceptually closest to CRG, are not compared even though the privacy experiments use PrivacyRestore's data splits, so it is unclear how much of the gain comes from the reference mechanism itself.
-
The experimental configuration is narrow. All results use a single 1B decoder, and the main utility and privacy results use a single noise level (ϵ=75), with privacy attacks only on DDx-Plus; there is no privacy-utility trade-off curve, no larger-model study, and no formal DP guarantee.
Questions for authors
Null
2 comments
Thank you for your thoughtful feedback and for reconsidering your assessment. Your comments have helped us improve the paper.
Thank you for the response. I will update my score in "Soundness" from 2 to 3.