- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper studies developing small language models in a local-cloud-local collaboration setting where local small models interact with more capable models in cloud to handle complex queries in a privacy-aware manner. For evaluation, the authors introduce a benchmark that consists of QA samples for assessing privacy leakage and task success for each query. The benchmark with 2,200 privacy-bearing queries is used to measure privacy leakage with attribute inference accuracy with an LLM attacker. For training, a two-step approach -- SFT initialization to learn basic anonymization followed by multi-objective GRPO -- designed to more explicitly consider privacy-utility trade-off is used. Experiments show favorable results against inference (adversarial anonymization) and training (AgentStealth) baselines.
Critical strengths
-
Benchmark for assessing privacy-utility trade-offs in local-cloud-local interaction settings across multiple QA domains. The authors carefully curate QA data across legal, medical, and open-ended domains used for their main evaluations. Compared to prior benchmarks, it is comparable in size and supports attribute inference accuracy and local-cloud collaboration performance.
-
The proposed training method is fairly straightforward and conceptually sound. The two-stage method where the first SFT step is used to learn basic anonymization followed by multi-objective RL to balance between privacy and utility is conceptually simple and straightforward to implement.
Critical weaknesses
-
Technical contribution in training and its impact on performance. Both the local-cloud-local setting and training that involves distillation and RL have been studied in prior work. It appears that the multi-objective GRPO that balances between privacy and utility is one of the main method contributions, but the methodological "delta" compared to prior work and its impact on performance should be more clearly discussed and evaluated.
-
While generalization to an unseen cloud LLM is evaluated with GPT-5-mini, it is unclear how the findings hold for much stronger unseen LLM attackers. The mini variant is considered by some to be fairly small (smaller than 27B), so it's possible that the local models trained against the 27B model might be sufficiently good for the mini model.
Questions for authors
Q. Have the authors evaluated the local models against stronger unseen LLMs?
2 comments
Gentle Follow-Up
Dear Reviewer UUiU,
Thank you again for your detailed review. As the discussion period ends on November 18, we wanted to check whether our response, with additional baselines, ablation experiments and explanation address your concerns. We would be grateful for any feedback, and happy to clarify further. If our response addresses your concerns, we would appreciate it if you would consider updating your assessment.
Best regards,
The Authors
Author Response (W1, W2/Q)
We thank the reviewer for the positive assessment and the two precise questions.
Table R24. The three training components and their measured effect
Table R25. λ sweep of the privacy weight
Measured impact of the stages. In paper Fig. 5(a) (4B), SFT gives the largest privacy gain at a utility cost, GRPO / MO-GRPO recover utility while giving part of the privacy back, and the full model (SFT + MO-GRPO with the entropy privacy reward) is significantly more private than the untrained AA loop (−6.7 AIA, p≤0.002) at comparable utility (+1.0, n.s.) with the same budget. The prompt-aligned baseline (72.3) and the rounds sweep (one trained round, 65.8, beats five untrained rounds, 71.5; reply to Cbtz W4) locate the gain in training rather than prompting; within training, the privacy gain comes from SFT, and RL trades part of it for utility. The λ sweep shows that the MO-GRPO balance is controllable. We will report the Fig. 5(a) values as a table in the main text.
Table R26. Calibration of the quantity used by the privacy reward (E[p_true]) vs attack accuracy (same log-probability run as Table R14; micro-averaged over the 2,003 probes; |Δ| computed before rounding)
We re-attacked the stored rewrites of all paper Table 3 methods with GPT-5.4, with a defense-aware GPT-5.4 (six original / rewrite / ground-truth examples), and, for Ours, with a white-box attacker holding the rewriter.
Table R27. Stronger and defense-aware attackers
GPT-5.4 is stronger by 4–7 pts (its gain is largest on oracle-redacted text, +8.4, negligible on raw text, +0.1, and only +1.1 prior-only, i.e. it extracts more from the residual context). The ranking is unchanged and Ours keeps the lowest AIA among the five Table 3 methods (−14.4 vs base, −6.6 vs AA, −4.4 vs TRACE-RPS, −2.4 vs AgentStealth; the last gap was not significance-tested, so we claim no privacy advantage over AgentStealth). Defense awareness adds no meaningful leakage for any method (27B within ±1.3, GPT-5.4 within ±0.8), and the white-box attacker reaches 66.0 (reply to mJT6 W2). The ordering relative to base, AA and TRACE-RPS is therefore preserved under a substantially stronger, defense-aware attacker.