- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper examines how to prevent other models from acquiring a language model's capabilities through its generated responses. The authors argue that making responses difficult to learn is not the only way to prevent knowledge transfer. They propose DISTILSHIELD, a framework that modifies the reasoning content of teacher responses to encourage students to learn patterns that do not generalize well. The method uses three main components to introduce these patterns, reduce useful knowledge transfer during training, and maintain their effects when students generate their own responses. The authors also introduce a training algorithm for optimizing the protection method. Experiments across multiple datasets and language models show lower student performance after distillation compared with the tested protection baselines, while maintaining much of the original response utility. More specifically, experiments use two teachers, six students, and six datasets in math, commonsense, and code. With the R1-7B teacher and a Llama 1B student, average student accuracy drops from 38.6 percent with normal distillation to 19.3 percent, below the zero-shot level, while teacher accuracy is unchanged.
Critical strengths
I think that the first strength is the new view of anti-distillation, which separates fitting the data from learning the skill. I think this is an original and useful idea for the area, and the ablations support it well. Moreover, the paper provides extensive experiments involving different models, datasets, and attack settings. The component removal experiments also help explain why the different parts of DISTILSHIELD are needed. Without a doubt, these results strengthen the evidence for the proposed approach.
Critical weaknesses
I noticed that the method requires additional training and response conversion, which may create practical costs for large-scale deployment. Although the paper reports computation times, I think that a clearer study of the cost for a real model service is needed. Moreover, the paper evaluates the protection against a selected set of distillation methods and attempts to overcome the defense. It remains unclear whether more adaptive attackers could identify the modified reasoning patterns, remove them, or recover useful information through other forms of training. This matters because the defense's long-term value depends on its reliability against evolving attack strategies.
Questions for authors
I am curious about the additional computational cost and response delay when using DISTILSHIELD in a real language model service, and how effective the protection would remain if an attacker specifically trained a model to identify and remove the introduced reasoning patterns. Also, please explain how well the defense holds when the attacker uses the preserved teacher answers as RL rewards, or trains only on answers.
2 comments
Response to Reviewer RVK2 (Part II)
Only using answers as training signal (Q3)
An attacker can indeed discard the rewritten reasoning and train only on question-answer pairs. However, this also discards the primary supervision signal in reasoning distillation. The setting then is degraded to answer-only fine-tuning or RL, which falls outside the LLM knowledge distillation setting that our work targets. For the same reason, prior anti-distillation works [1,2] do not consider this setting. For completeness, we report the results below. Answer-only SFT performs poorly (12.7% on average), even below distillation from the protected responses. Answer-only RL performs better but still falls 6.5 (RLVR) and 7.7 (GRPO) below distillation from the vanilla teacher with reasoning on average, yielding little gain on MBPP. This confirms that bypassing the defense by discarding the reasoning causes an inevitable cost to the attacker, whether the answers are used for fine-tuning or as RL rewards. More importantly, the answers serve only as correctness labels, and such labels are often obtainable without a teacher (e.g., from public datasets or human annotations).
Table: Distillation with different data components and methods
| Setting | GSM8K | Math | MBPP |
|---|---|---|---|
| Clean (reasoning + answer) | 47.9 | 31.1 | 30.9 |
| Protected (reasoning + answer) | 21.1 | 16.5 | 20.1 |
| Answer only w/ SKD | 7.2 | 10.1 | 20.8 |
| Answer only w/ RLVR | 42.6 | 26.6 | 21.2 |
| Answer only w/ GRPO | 41.0 | 24.3 | 21.4 |
We hope our response addresses the reviewer’s concerns, and we are glad to engage in any further discussion!
[1] Savani, Yash, et al. "Antidistillation sampling." Advances in Neural Information Processing Systems 38 (2026): 117800-117827
[2] Li, Pingzhi, et al. "Doge: Defensive output generation for llm protection against knowledge distillation." arXiv preprint arXiv:2505.19504 (2025)
Response to Reviewer RVK2 (Part I)
We sincerely appreciate Reviewer RVK2's recognition of our work and the valuable feedback. We provide a further response to each point below:
We thank the reviewer for the valuable feedback. Regarding training, the converter is trained only once per dataset, taking about five hours on a single A100 GPU (Table 5). This one-time cost is amortized across all subsequent queries. Regarding serving, our efficiency analysis (Section 5.6 and Table 12) shows that the converter adds only 0.134 s per response, about 20% of the teacher’s own generation time.
To further address the reviewer’s concern, we deploy both the vanilla and the defensive teacher as API services with vLLM and measure additional metrics at different levels of concurrency. To simulate a real-world scenario, we randomly sample 1,000 queries from the six datasets and warm up each service with 50 queries. As shown in the table below, DistilShield increases p50 latency by 3.0-3.8 s (17%-24%) and decreases request throughput by 14%-16%, while token throughput is fully maintained. Importantly, the relative overhead does not increase with concurrency, as the p50 overhead decreases from 24% to 17% as concurrency rises from 1 to 32. Moreover, since the 3B converter incurs a fixed cost independent of the teacher, this overhead is measured against a relatively small 7B teacher and would be marginal for much larger commercial models, which is a desirable property for real-world deployment.
Table: Serving cost under different concurrency levels
We appreciate the reviewer’s constructive feedback. We further consider two progressively stronger adaptive attacks, which are practical:
As shown in the table below, standard sanitization backfires on the attacker, degrading the vanilla-distilled student by 19.4 points and the defensive student even further to 21.5%. Therefore, generic rewriting (e.g., paraphrasing or standard sanitization) cannot distinguish the implanted shortcut from the useful content. Privileged sanitization can partially recover 2.4 points of capacity from the defensive teacher, despite requiring rarely available clean responses. These results indicate that the protection is not tied to easily removable artifacts.
Table: Stronger adaptive attacks on GSM8K