- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes LADS, a defense against multi-account model distillation. The main idea is to couple sampling randomness across accounts while preserving the original output distribution for each individual account. The authors provide a theoretical analysis and evaluate the method on image generation, mathematical reasoning, and code generation.
Critical strengths
-
I liked the main idea of controlling sampling randomness rather than modifying model outputs. Preserving the single-account user experience while reducing the effectiveness of multi-account distillation is an interesting direction.
-
The experiments show promising results across both diffusion and language models. The theoretical analysis also provides a useful perspective on how correlated training samples affect effective sample size.
Critical weaknesses
-
My main concern is the theoretical guarantee. Theorem 3.2 appears to rely on balanced center-depth weights, as clarified in Appendix C.8, but this condition is not stated explicitly in the main theorem. Also, a weaker generalization upper bound does not necessarily establish that the student's actual generalization error must increase.
-
The effectiveness against adaptive distillers remains unclear. As the authors acknowledge in Section 3.3, an attacker could modify queries to reach different semantic buckets or change query allocation across accounts. The experiments mainly consider noisy bucket assignments rather than these adaptive strategies. This limits the practical security conclusions.
Questions for authors
-
Could the authors clarify the balanced-weight assumption in Theorem 3.2? Does the claimed effective sample size reduction still hold when query frequencies across buckets are highly uneven?
-
How robust is LADS when the distiller deliberately distributes queries across different semantic buckets or changes the query order across accounts?
-
In Table 2, the reported improvements differ from the numbers discussed in Section 4.2. Could the authors correct these values and clarify the actual performance reductions?
2 comments
Dear reviewer,
Thank you for your constructive review and comments! We have provided point-to-point responses to your review. Considering the author-reviewer discussion is ending very soon, could you kindly take a look at our responses and let us know your feedback? We are happy to discuss more if you still have any concerns. Thank you again and look forward to your feedback.
We thank the reviewer for the careful reading. Distillation is increasingly recognized as a major threat to commercial LLM providers. Anthropic was even speculated to have downgraded Claude’s response quality to mitigate distillation attacks, drawing substantial public criticism. As the first lossless anti-distillation method, we believe our work opens a timely research direction, and we hope the reviewers will take its exploratory nature and potential impact into consideration.
Weakness 1: Interpretation of theory
Thanks for raising the question. A central contribution of generalization theory is to provide “high-probability guarantees” for learning tasks. In our case, standard i.i.d. sampling provides a stronger high-probability guarantee on test loss than LADS, and the bound is tight up to constant factors. See lines 229–231 of the paper. Such comparisons of statistical guarantees are standard and meaningful in learning theory, although they do not imply that “the student’s actual generalization error must increase” for every distribution. This is why experiments are still necessary. Our results show that LADS consistently reduces distillation effectiveness across both image and language generation tasks, providing direct empirical evidence of its practical impact.
Question 1: Technical issues
Thanks for raising this question. The balanced case in Theorem 3.2 gives a concise form of the general weighted analysis in Appendix C.7–C.8. Under clean assignments, uniform weights maximize neff for a fixed set of cells; the general bound tracks the actual weights when query frequencies are uneven.
The source of sample compression is the reuse of randomness across accounts, and the weighted analysis measures how often each draw is reused. We will state the balancing condition explicitly and clarify this connection in the paper.
Question 2: Robustness
We did consider how to evaluate the robustness of our algorithm and explicitly discuss the challenges of experimental design in the paper (lines 349–351). A key practical consideration is that distillers typically lack full knowledge of the provider’s sampling strategy, including the exact bucket assignments and implementation details. Recovering this information through reverse engineering can also be challenging. We therefore incorporate noisy semantic mappings into our experiments as one way to model this uncertainty. This experimental design is also intended to address the concern raised in Weakness 2.
The adversarial strategy described in Question 2 does not eliminate the cross-account coupling in LADS. Under Algorithm 2, queries from different accounts share randomness whenever their bucket assignments and within-bucket visit counts match. Reordering queries changes which queries are coupled, but preserves this mechanism.
For example, consider two accounts: account 1 submits queries q11 and q12, while account 2 submits q21 and q22. Suppose all four queries fall into the same bucket. If both accounts submit their queries in the original order, q11 shares randomness with q21, and q12 shares randomness with q22. If account 1 reverses its query order, q12 instead shares randomness with q21, and q11 shares randomness with q22.
In both cases, the four responses are generated using only two independent randomness realizations. Thus, query reordering preserves the reduction in independent randomness underlying the collected responses.
To be honest, we have put considerable effort into designing experiments that capture realistic attack–defense interactions in model distillation. We would welcome further suggestions on the experimental design and would be happy to incorporate them into our evaluation.
Question 3: Numbers mismatch
Thank you for pointing out this inconsistency. The numbers in Table 2 are correct, but we forgot to update the corresponding values in Section 4.2. We will revise the text to match the table.