- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes SHADOWMASK, a training-time backdoor attack on masked diffusion language models. On poisoned examples, it replaces the standard all-mask corruption prior with a trigger–mask mixture and derives a corresponding weighted denoising cross-entropy objective. The attack assumes control over the training pipeline while retaining the model’s original inference procedure.
Critical strengths
-
The method explicitly modifies the categorical corruption process rather than only inserting trigger–target examples.
-
The evaluation includes pretraining, selective fine-tuning, and parameter-efficient fine-tuning, with experiments across multiple datasets and model families.
Critical weaknesses
-
Modifying the forward diffusion process and its terminal distribution to associate a trigger with a target, followed by deriving a compatible training objective, is already central to prior diffusion backdoor work such as BadDiffusion. SHADOWMASK adapts this principle to discrete masking, but the resulting objective remains a weighted cross-entropy loss. In the main small-model setting, effectively replaces mask corruption with trigger-token corruption on poisoned examples. The paper does not sufficiently establish what new capability or insight this adaptation provides beyond the existing principle.
-
Section 4 grants the attacker control over training data, corruption, and optimization, and assumes that the victim adopts the resulting checkpoint after checking clean utility. This is a legitimate supply-chain threat model, but it does not establish an attack available to an external API user or an adversary controlling only a small amount of public data. Under such broad training control, the central question is whether the proposed method provides a substantial advantage over strong alternative backdoor-training methods while surviving meaningful downstream checks. The current evidence only partially answers this question. Moreover, the reported ASR measures target-text generation, not successful execution of a harmful action or compromise of a deployed system.
-
The derivation assumes a trigger state outside the clean prediction support and introduces a modified reverse kernel. In practice, triggers are existing vocabulary tokens, and generation uses the original model-specific sampler rather than the derived kernel. Consequently, the derivation establishes an objective for the analytical construction, but does not directly explain why its practical realization reliably transfers to ordinary sampling. This limits the explanatory value of the theoretical contribution; it is not, by itself, evidence of a mathematical error.
-
The matched-budget small-model data-poisoning baseline is useful, but the large-model results in Tables 1, 9, and 11 primarily compare clean and backdoored models. They therefore establish feasibility rather than comparative advantage. There is also no direct comparison with the acknowledged concurrent work BadDLM. Furthermore, the ablations focus on target length and sampling steps, rather than the central trigger–mask mixture or controls matching trigger exposure.
Questions for authors
-
What specific capability or insight does the proposed discrete corruption construction provide beyond adapting the forward-process manipulation used in prior diffusion backdoor methods?
-
Can you compare SHADOWMASK with standard poisoning and a representative corruption-aware DLM attack on the larger models, using matched training budgets, poisoned examples, and clean-utility constraints?
-
Which parts of the theoretical argument remain applicable when the trigger belongs to the ordinary vocabulary and deployment uses the original sampler? Can controlled experiments clarify the mechanism connecting these two settings?
-
In the intended supply-chain scenario, what downstream validation or adaptation is the malicious checkpoint expected to survive, and what advantage does SHADOWMASK retain over simpler backdoor-training alternatives under those conditions?
2 comments
W4.2. Ablation study on trigger-mask mixture or controls matching trigger exposure.
We would like to clarify that is not a tunable hyperparameter but a mathematical variable introduced in our derivation to distinguish two corruption mechanisms: corresponds to SHADOWMASK, whereas corresponds to standard masking in clean models or a data-poisoning attack. Thus, is not a hyperparameter subject to tuning.
The two factors are also not independently configurable, as a corrupted position enters the trigger state with probability . Importantly, SHADOWMASK does not introduce additional training signals: the total corruption probability remains regardless of . Instead, SHADOWMASK reallocates the corruption probability mass from the standard mask state to the trigger state.
Therefore, the comparison between and serves as a controlled ablation that isolates the effect of the proposed corruption mechanism, while keeping the number of poisoned examples, corruption schedule, model architecture, training budget, and target fixed (Appendix E.3). Furthermore, our target-only control experiment shows that the target text alone does not induce the backdoor behavior, yielding ASRs of only 0.0% and 0.4% (Appendix E.5.2).
Q4.2. Robustness against downstream validation.
We evaluate whether a malicious checkpoint can survive two common downstream scenarios: (1) validation on clean inputs and (2) adaptation through clean fine-tuning or input preprocessing.
First, clean-input validation. SHADOWMASK largely preserves clean utility, with average judge scores differing by at most 0.16 across four large models (Table 1). We also observe no false positives on non-triggered inputs. Furthermore, the predictive KL divergence between clean and backdoored models on identical latent states is only 0.0599–0.0649, close to the 0.0557 divergence between two independently trained clean models (Table 14). These results suggest that ordinary clean-input validation may not reveal the backdoor.
Second, downstream adaptation. Section 5.5 evaluates robustness to clean fine-tuning, random token dropping, and paraphrasing. Notably, after 75,000 clean fine-tuning updates, SHADOWMASK retains an ASR of 86.18%, compared with only 15.26% for dataset-only poisoning. Its generation perplexity also remains lower than that of the baseline throughout fine-tuning (12.49 vs. 13.62 at 75,000 updates; Table 13).
Together, these results demonstrate that SHADOWMASK can preserve clean utility while surviving the downstream adaptation methods evaluated in our experiments. We will consolidate these findings in the revision to clarify the downstream threat model and its experimental support.
We sincerely thank you for your thoughtful feedback and constructive questions. We hope our responses have satisfactorily addressed your concerns. If so, we would greatly appreciate it if you could consider raising your score.
We thank Reviewer fAqH for the critical questions to help us improve the paper.
W1 & Q1. Novelty compared to BadDiffusion. Why is it not a straightforward application of BadDiffusion?
BadDiffusion and SHADOWMASK share the high-level idea of modifying diffusion processes to implant backdoors. However, SHADOWMASK is not a straightforward application of BadDiffusion because the two methods operate on fundamentally different diffusion mechanisms. BadDiffusion targets continuous Gaussian diffusion models and introduces trigger-dependent distribution shifts into their forward and reverse processes. In contrast, MDLMs employ discrete, mask-based corruption, for which BadDiffusion's Gaussian formulation is not directly applicable. SHADOWMASK addresses this difference by introducing a trigger-specific corruption state into the discrete diffusion process, reallocating corruption probability mass from the standard mask state to the trigger state without increasing the overall corruption probability. Moreover, this formulation allows the trigger to be denoised into natural tokens and disappear from the generated output. Thus, although both approaches manipulate diffusion processes, SHADOWMASK requires a distinct mathematical formulation tailored to masked discrete diffusion and introduces a different mechanism for trigger activation and removal.
W2.1 & Q2 & W4.1 & Q4.1. Compare SHADOWMASK with standard poisoning, and a representative corruption-aware DLM attack on larger models.
We have extended our comparison with BadDLM to LLaDA2.0-mini (16B total parameters), the largest model in our evaluation and larger than any model evaluated in BadDLM, whose largest model is LLaDA-8B. Under matched conditions, including the same 1% poisoning rate, trigger, target payload, trainable parameters, and training budget, BadDLM achieves an ASR of 63.8%, whereas SHADOWMASK achieves 100%.
Our previously reported comparison on LLaDA-8B corresponds to the largest model evaluated in the BadDLM paper. Using the sudo trigger and a 1% poisoning rate, BadDLM achieves an ASR of 52.4%, compared with 100% for SHADOWMASK.
These results demonstrate that SHADOWMASK consistently outperforms BadDLM across both model scales.
W2.2. ASR only evaluates target-text generation, not the actual execution of the harmful action.
We thank the reviewer for raising this important point. We acknowledge that ASR measures successful generation of the target payload rather than its actual execution. However, generating the malicious payload is a necessary condition for its execution in our threat model. Therefore, ASR provides an upper bound on the probability of successful execution.
This evaluation protocol is consistent with the established backdoor attack literature, where attack success is typically measured at the model-output level rather than by downstream real-world consequences. For example, backdoor attacks against traffic sign classifiers evaluate whether a triggered stop sign is misclassified as a speed-limit sign, rather than whether the misclassification ultimately causes a traffic accident. Similarly, our evaluation focuses on whether the backdoored model generates the attacker-desired payload, without assuming that the payload is necessarily executed.
W3 & Q3. Out-of-vocabulary trigger in theory vs. in-vocabulary trigger in practice.
Eq. (6) is an analytical formulation used to derive the training objective of the denoising network rather than a sampler, and under BD-SUBS the true and learned reverse kernels share the same corruption-state probability mass, so those terms cancel in the KL of Eq. (7) and the clean-token denoiser xθ is the only learned quantity. Modifying the forward process therefore changes which corrupted states xθ is trained on, not how sampling proceeds: the deployed sampler is unchanged, and the attack transfers because the trigger-target association is carried in the denoiser weights. On the support question, ⟨xθ,g⟩=0 (BD-SUBS-1) is an idealization that keeps {m,g} disjoint from the prediction target. With an in-vocabulary rare token, it holds approximately, the residual being the mass xθ places on g, which is on the order of the trigger's frequency in clean text: 0.1327 and 0.6770 occurrences per million tokens for
scootedandsmirked(Appendix E.4). Our reported results already include that harder in-vocabulary case in addition to an added token (Appendix E.4), so they are obtained under the approximate condition and not the idealized one, and we will state the approximation and its residual explicitly in Appendix F. Our empirical results demonstrate that our method can work for both Out-of-vocabulary and in-vocabulary triggers.