- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes BadDLM, a training-time backdoor framework for diffusion language models. For poisoned prompt–response pairs, it identifies response positions associated with the attack target and increases their corruption probability during fine-tuning. The authors show that a normalized exponential weighting of mask patterns is equivalent to sampling from a modified, factorized corruption distribution. Experiments on LLaDA and Dream, with an additional concept-injection experiment on DiffusionGemma, report high attack success, low false activation, and largely preserved clean benchmark performance.
Critical strengths
-
BadDLM introduces a simple modification to the corruption process that increases reconstruction supervision at target-relevant positions. The equivalence between normalized exponential weighting and the induced Bernoulli distribution makes the intervention mathematically explicit and straightforward to implement.
-
The experiments cover four attack objectives on two instruction-tuned DLMs and show substantial improvements over the evaluated baselines. Additional utility benchmarks, repeated runs, false-trigger measurements, and human harmfulness evaluation provide useful support for the reported effectiveness and utility preservation.
Critical weaknesses
-
The ExpIW ablation does not clearly implement the objective derived in Section 3.2. The theoretical weight depends on the number of masked target positions and includes a normalization term, whereas Appendix C.7.4 describes weighting each poisoned sample by exp(k), where k is the total number of special tokens. As described, these are different objectives, so Tables 17–18 do not isolate the benefit of replacing explicit weighting with direct sampling under an equivalent objective.
-
SHADOWMASK already study forward-corruption backdoors in MDLMs. Without a direct comparison or clear technical justification, BadDLM’s incremental contribution and “new attack surface” claim remain insufficiently established.
Questions for authors
-
Please clarify whether ExpIW uses the exact weight derived in Section 3.2. Does the advantage of direct sampling persist when the objectives and training budgets are matched?
-
Could the authors compare BadDLM with SHADOWMASK on a common attack task under matched experimental conditions? If not, what prevents a meaningful comparison?
5 comments
Response to Reviewer cWYU [Part 2]
W2: SHADOWMASK already studies corruption-based MDLM backdoors, so the technical contribution and “new attack surface” claim need clarification.
Thank you for highlighting this overlap. SHADOWMASK [1] also studies corruption-based MDLM backdoors. Our contribution differs along two dimensions.
(1) Diffusion process (appropriate scope). SHADOWMASK targets masked diffusion language models (MDLMs). BadDLM's trigger-aware objective and induced corruption distribution extend to uniform diffusion language models (UDLMs). $\color{blue}{\textbf{Section 3.3}}$ formulates corruption through a replacement distribution $\nu$: the same normalized tilt changes the resampling rate at target-relevant positions while leaving $\nu$ unchanged. Choosing $\nu=\delta_{\texttt{[MASK]}}$ recovers masked diffusion, while $\nu=\mathrm{Unif}(\mathcal V)$ gives uniform diffusion. $\color{blue}{\textbf{Appendix B.3}}$ provides the full replacement-kernel derivation and objective equivalence. $\color{blue}{\textbf{Table 3}}$ ($\color{blue}{\textbf{Section 4.2}}$) of the revision validates this extension on DiffusionGemma-26B-A4B-it for Concept injection.
(2) Backdoor target and capability. SHADOWMASK supervises the same tokens at fixed response positions, through a fixed prefix or a fully replaced output. BadDLM supports flexible responses that realize Concept, Attribute, Align, or Payload targets, with target-relevant positions $S(u,y_0)$ annotated separately for each training pair ($\color{blue}{\textbf{Section 3.4}}$).
$\color{blue}{\textbf{Appendix B.4}}$ formalizes this distinction. Proposition 1 states that, on the poisoned branch, Bayes-optimal predictions at positively supervised fixed target positions are point masses on the prescribed tokens, assuming finite Bayes risk and a prediction class permitting arbitrary token distributions independently at each observation and position. For a target string $T$ of length $k$, the occurrence criterion is
$$
\mathcal C_{\mathrm{occ}}(T)=\bigcup_{r\ge1}\{y:|y|\ge r+k-1,\ y_{r:r+k-1}=T\}.
$$
Fixed-prefix matching is exactly the $r=1$ term. Thus the fixed-prefix target of SHADOWMASK is a special case (subset) of the occurrence target used by Concept and Payload. Proposition 3 further shows that, on a finite evaluation set where every input admits two responses sharing the matched prefix but having opposite behavioral outcomes, behavioral ASR can take any value in $[0,1]$ despite perfect prefix matching.
The four targets differ from fixed-prefix reconstruction as follows:
- Concept: The concept can occur anywhere it fits naturally in the response. Requiring every recommendation to begin with “Nike” constrains sentence structure and can make it unnatural.
- Attribute: Success depends on the full response's attitude toward the input topic. A fixed opening does not determine whether the continuation expresses the target attitude.
- Align: Success depends on the full response's harmfulness conditioned on the request. The same affirmative opening can precede either prohibited content or a safe refusal. We test this point experimentally below.
- Payload: The specified code pattern can occur at positions appropriate to each generated program. A fixed prefix does not capture this positional flexibility, while Payload success is measured by the occurrence of the pattern.
We forcibly adapt SHADOWMASK to Align using a fixed prefix beginning with “Of course,” and evaluate both methods with the same full-response Align judge. $\color{blue}{\textbf{Tables 1–2}}$ ($\color{blue}{\textbf{Section 4.2}}$) of the revision show that SHADOWMASK reaches 62.4% Align ASR on LLaDA and 66.8% on Dream, about 25 to 30 points below BadDLM (91.8% and 91.3%), while utility stays comparable on LLaDA and equal on Dream. This result shows that fixed-prefix training does not suit our more realistic behavioral targets. Its fixed-string target does not readily extend to Concept, Attribute, or Payload, so SHADOWMASK was not evaluated on those targets ($\color{blue}{\textbf{Section 4.1}}$).
Response to Reviewer cWYU [Part 3]
Q1: Does the advantage persist with the exact weight and matched training budgets?
See our response to W1.
Q2: Can the methods be compared on a common attack task under matched experimental conditions?
To answer your question, we compare SHADOWMASK and BadDLM on alignment bypass (Align) with LLaDA-8B-Instruct and Dream-Instruct-7B under matched training conditions ($\color{blue}{\textbf{Tables 1–2}}$): the same training set of 4,000 samples, a 10% poisoning rate, 5 epochs, and the trigger “sudo”. The methods differ only in their training target and objective. SHADOWMASK uses a fixed prefix beginning with “Of course,” while BadDLM uses the request-dependent Align construction in $\color{blue}{\textbf{Section 3.4}}$.
Both are evaluated with the same full-response Align judge conditioned on the request. A harmfulness score of 4 or 5 counts as success ($\color{blue}{\textbf{Appendix C.9.1}}$), so matching the prefix followed by a safe refusal counts as failure. $\color{blue}{\textbf{Tables 1–2}}$ ($\color{blue}{\textbf{Section 4.2}}$) of the revision show that SHADOWMASK reaches 62.4% Align ASR on LLaDA and 66.8% on Dream, about 25 to 30 points below BadDLM (91.8% and 91.3%), while utility stays comparable on LLaDA and equal on Dream.
Reference:
[1] Daniel Yiming Cao, Chengzhong Wang, Sheng-Yen Chou, Chengyu Huang, Pin-Yu Chen, Shengwei An. Backdooring Masked Diffusion Language Models. arXiv preprint arXiv:2605.19262, 2026.
Response to Reviewer cWYU [Part 1]
Thank you for your detailed review and suggestions. We appreciate your recognition of our simple and mathematically explicit modification to the corruption process, and our experiments across four attack objectives with substantial improvements over the baselines. Below, we respond to the comments in Weaknesses (W) and Questions (Q).
W1: The Exp IW ablation uses a different objective from the normalized mask-pattern weighting.
Thank you for this detailed comment. The original Exp IW does not use the exact weight derived in Section 3.2. Specifically, it multiplies the poisoned-sample loss by exp(k), where k is the total number of special tokens. To compare direct sampling with explicit weighting under the same objective and the same training budget, we add Exp_normal IW, which uses the exact normalized weight.
Exp_normal IW samples masks from qstd and multiplies the denoising loss by:
wλ(m,u,y0,ρ)=exp(λ∑i∈S(u,y0)mi−∣S(u,y0)∣log(1−ρ+ρeλ))
Here λ is the tilt strength of the induced masking (BadDLM in Algorithm 1), mi indicates whether position i is masked, ρ is the masking rate, and S(u,y0) contains target-relevant positions. Theorem 3.1 and Corollary 3.3 establish equality between this weighted objective and direct induced-mask sampling with the original denoising loss. Appendix C.7.4 now distinguishes the two weighting baselines explicitly.
We report Exp_normal IW together with Exp IW and BadDLM under matched 5-epoch training on LLaDA-8B-Instruct in Table 6 (Section 4.5) and Table 19 (Appendix C.7.4) of the revision. Exp IW and Exp_normal IW give similar results. Both have slightly lower ASR than BadDLM on every target and slightly lower utility than BadDLM. Since Exp_normal IW optimizes the same normalized objective as BadDLM, these results are consistent with Theorem 3.1 and support the role of the induced masking derived in Section 3.
We also add the every-two-epoch training trajectories of Exp_normal IW to Table 20 (Appendix C.7.5) of the revision. Table 20 shows that BadDLM reaches high ASR in fewer epochs than Exp_normal IW. This agrees with Section 3.3, which notes that directly weighting training samples may cause high-variance batch updates, whereas sampling from the induced masking distribution enables smoother updates. It provides further empirical support for our derivation. Section 4.5 connects this observation to the smoother-update motivation in Section 3.3.