- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies antidistillation through a game-theoretic framework between a utility-constrained teacher and an adaptive student. The teacher releases a defended output distribution while remaining close to a reference model, and the student adaptively reweights released examples under a KL-constrained adaptation budget. The framework yields exponential-tilting best responses for both sides. On the attacker side, the student emphasizes examples with high estimated downstream learning value; on the defender side, the teacher suppresses examples that are most useful for distillation. Based on a likelihood-gap proxy for example value, the authors derive a lightweight Product-of-Experts (PoE) defense that combines teacher and proxy-student probabilities during decoding.
Critical strengths
- The paper identifies an important evaluation weakness in prior antidistillation work by showing that adaptive students can recover substantially more capability than passive students.
- The minimax formulation provides a clean and interpretable framework that unifies adaptive sample reweighting and teacher-side defense under explicit fidelity and adaptation budgets.
- The proposed PoE defense is computationally attractive, requiring only forward passes while achieving adaptive leakage comparable to the substantially more expensive ADS baseline.
Critical weaknesses
- The paper does not sufficiently distinguish the one-sided teacher best response used to motivate PoE from the solution of the full Stackelberg minimax game.
- The statement of Theorem 3.1 appears to omit assumptions needed for claims such as uniqueness of the dual variables and for the finite-dimensional convex analysis used in the proof.
- The implemented adaptive attack differs from the population-level KL-constrained best response because it dynamically recomputes values and normalizes weights within minibatches, while the resulting effective adaptation budget is not reported.
- The empirical evidence is limited to two mathematical reasoning benchmarks and a single main teacher/student configuration, making the generality of the conclusions unclear.
Questions for authors
- What additional assumptions are needed for Theorem 3.1, especially for the uniqueness of the dual variables?
- Can you report the effective KL adaptation budget of the adaptive attack used in the experiments?
- How sensitive is the adaptive attack to the amount of held-out downstream data used to compute the value scores?
We thank the reviewer for engaging, and respond to their comments below. We also refer the reviewer to the revised version of the submission we uploaded.
We agree that this distinction should be clear, and we note that it is already stated immediately after Theorem 3.1, but we will recall it again when introducing PoE. For reference, recall that PoE instantiates the one-sided teacher response for a fixed proxy value function, and we do not claim it solves the full Stackelberg minimax game, which is analyzed separately in Appendix B.
We agree that Theorem 3.1 could be clearer about the active KL constraints. We added a finite data space (i.e., the prompt-output pairs) assumption for simplicity, noting that general prompt distributions can be handled under suitable measurability and integrability conditions. We also dropped the parameter uniqueness claim, which is unnecessary for deriving the best-response formulas. Boundary cases such as zero or sufficiently large KL budgets are now treated separately in the appendix.
We acknowledge in Section 3.1 that our attack is a practical approximation of the theoretical best student response, given that computing the exact population best response requires scoring and normalization over the teacher’s full output distribution, which is computationally impractical. We therefore normalize within minibatches and update values as the student learns. This suffices for our empirical goal of demonstrating that passive evaluation can underestimate leakage, and is informed by our theoretical framework.
We agree that our empirical results focus on mathematical reasoning, which we acknowledge in the introduction. There, we mention that we follow Savani et al. (2025)’s mathematical reasoning setting to measure the influence of attacker adaptation only, keeping the rest fixed. Regarding teacher/student configurations, we additionally show in Appendix C.4 an adaptive–passive gap with a smaller defense proxy. Evidently, broader task and teacher/student coverage would be great future work.
We agree and now acknowledge in the revised submission that the distillation attack could be used by strategic actors, although our purposes are scientific.
The KL adaptation budget is mostly a theoretical instrument to model the fact that the adversary may adapt (or not) to different degrees. This budget is dual (i.e. its Lagrange multiplier) to the “sharpness” hyperparameter, for which we found 0.5 to be usually a good value.
We ran a new ablation suggesting that substantially fewer holdout traces suffice in this setting. We varied the holdout size on GSM8K with ADS λ=0.05, β=0.5, keeping the student initialization, training budget, and 1,209 test questions fixed.
With 100 holdout traces, which is less than 2% the total data available to the student for SFT, we observe no significant accuracy drop. Note this is for a single seed so small differences are insignificant.