- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper introduces Indirect Harmfulness Optimization (IHO): a jailbreak method which builds on Inpainting (Lüdke et al. 2025) by adding DPO on feedback from an LLM judge to optimize the diffusion LLM. They also introduce a 6 dimensional framework for holistic evaluation of jailbreaks. Under this framework, they find that IHO has strong transfer across behaviors and is efficient at using few samples at inference time.
Critical strengths
The premise of doing RL to improve the attacker model makes sense, and it seems that this has indeed improved the attack success rate compared to Inpainting. The results on GLM are particularly impressive.
It is good to see a human audit of the attack success labels, particularly since the attacker model was optimized against an LLM judge, and this found minimal reduction in ASR on the undefended models at least.
Critical weaknesses
The attack is not incredibly novel. We have RL trained attackers and diffusion LLM attackers in the literature, this work just combines the two. The six axis framework is particularly well written, but again these are standard considerations in the literature. The level of contribution here feels more like a workshop paper. I would have liked to see a more thorough set of ablations (e.g. are there different ways to apply the attack to a classifier-defended model) and baselines (e.g. AdvGRPO or DC-GRPO) for a conference paper.
I think it is a shame that the authors could not apply their attack to GPT or Claude. I think it makes it harder to support the strong claims around this attack requiring only black box access, transferring across models and being easy to apply.
Questions for authors
- Where should I be looking for evidence of the claim that attacks transfer well across models with similar defenses? Is it just Llama vs. Qwen32? I would like to see a greater range of models than this. The more impressive transfer is from Qwen to GLM later, but this still leaves a poorly evidenced claim in section 5.2.
- Figure 5 seems to be missing training step labels? Is (b) cycle 0 vs (c) cycle 6 for instance?
- It is suspicious that IHO performs better on held-out behaviors. You say this is because they are “slightly easier on average”. If so, it would be good to correct this bias with better sampling.
- What is going on with the spikes in Figure 5a?
- I’m not sure what the overall point of section 5.4 is. It seems very obvious that judge scores need to go up during training. I’m not sure why it really matters that output perplexity is going down, or why it is presented in this way rather than say a line plot with training step on the x axis.
- The most interesting section is 5.5 but only warrants 2 short paragraphs. I would like more analysis here. Why does training on Qwen work better, why does IHO outperform JR1 by so much here when they looked so similar in Table 1, etc.
7 comments
W3: Attacking Models from OpenAI
I think it is a shame that the authors could not apply their attack to GPT or Claude. I think it makes it harder to support the strong claims around this attack requiring only black box access, transferring across models and being easy to apply.
We performed an additional attack evaluation with OpenAI Luna on GuidedBench [1] (see also general comment). Moreover, we are now able to also demonstrate policy transferability for Gemma and Muse finetuned models.
We trained IHO attackers on Gemma-4-31B and on Muse-Glimmer-30B and evaluated each against Gemma-4-31B, Muse-Glimmer-30B and Muse-Spark-Open-816B-A42B, using the same protocol as in the main experiments. Here we used GuidedBench with DeepSeek 4.1 Flash as a judge, which evaluates responses against detailed, behavior-specific rubrics and has an even lower false-positive rate than the judge used in our main experiments [1]. We report the mean harmfulness score, the fraction of behaviors with at least one attack scoring ≥ 0.5, and the fraction fully broken (an attack scoring 1).
| Attacker | Target | Mean score | Behaviors with attack ≥ 0.5 | Behaviors fully broken |
|---|---|---|---|---|
| Gemma | 0.337 | 92.2% | 57.2% | |
| trained on Gemma | Muse Glimmer | 0.201 | 77.8% | 43.9% |
| Muse Spark | 0.111 | 56.1% | 21.1% | |
| Gemma | 0.284 | 83.3% | 38.9% | |
| trained on Muse | Muse Glimmer | 0.279 | 80.0% | 44.4% |
| Muse Spark | 0.164 | 61.1% | 25.0% |
These results support our claim that policies learned by IHO are not tied to the model they were optimized against and apply across model families. Moreover, it is evidence of IHO working on the separate dataset GuidedBench that uses a stricter judge policy.
Additionally, we have extended API based results further by attacking Gemini 3.8 Flash and Qwen 3.8 Flash:
| Target | Method | Judge ASR | Precision-corrected ASR* |
|---|---|---|---|
| Gemini 3.8 Flash | IHO | 95.0% | 90.8% |
| Gemini 3.8 Flash | JR1 | 55.0% | 45.6% |
| Gemini 3.8 Flash | Inpainting | 42.5% | 30.6% |
| Qwen 3.8 Flash | IHO | 82.5% | 71.3% |
| Qwen 3.8 Flash | Inpainting | 22.5% | 8.7% |
| Qwen 3.8 Flash | JR1 | 7.5% | 7.5% |
*Rough estimate for the rebuttal only, computed with the precision correction from the submission. See the global comment and our response to Reviewer zFr5 (W1) for its limitations. We will replace it with human-verified ASR.
IHO continues to demonstrate substantial improvements over baseline methods on these newer models.
Action: We added the new transfer experiments, the results on GuidedBench and the additional API runs to the paper.
Q1: Transfer Capabilities of IHO
Where should I be looking for evidence of the claim that attacks transfer well across models with similar defenses? Is it just Llama vs. Qwen32? I would like to see a greater range of models than this. The more impressive transfer is from Qwen to GLM later, but this still leaves a poorly evidenced claim in section 5.2.
Section 5.2 refers to Figure 3 and the full transfer matrices in Appendix I.3 (Figs. 17–22), which cover all 8×8 source–target pairs, not only LLaMA and Qwen-32B. For models with similar defenses, e.g. on held-out behaviors (Fig. 20, ASR(512, 0.8)), the CB-trained policy reaches 0.55 on CB+D, 0.57 on LAT and 0.50 on CAT, while the best baseline reaches 0.20, 0.38 and 0.45. In addition, W3 above reports new cross-family transfer between Gemma-4-31B and the Muse models.
Q2: Figure 5 labels
Figure 5 seems to be missing training step labels? Is (b) cycle 0 vs (c) cycle 6 for instance?
Yes, please excuse the missing annotation. An extended version of (b) and (c) can also be seen in Figure 15. We will extend this plot to remove ambiguity.
Q3: Training split
It is suspicious that IHO performs better on held-out behaviors. You say this is because they are “slightly easier on average”. If so, it would be good to correct this bias with better sampling.
We agree that IHO performing better on holdout data is suboptimal. However, we initially sampled randomly after stratifying by category and only discovered the difficulty imbalance during evaluation. We therefore consider reshuffling the data and retraining after observing performance to be bad practice. To resolve suspicion, we compare all methods on their train and heldout split performance in Table 1. The pattern is widespread: 35 method × target pairs (56.5%) perform better on holdout data, 10 (16.1%) perform equivalently, and only 17 (27.4%) perform worse. IHO performs at least as well on holdout for 6 of 8 targets (75%) and is thus close to the overall rate of pairs performing at least as well (72.6%).
Action: We will note this in the paper to avoid raising suspicion on data leakage.
Q4: Means in Figure 5a
What is going on with the spikes in Figure 5a?
The spikes are the means. We apologize for the missing legend.
Action: We will mark them more clearly with dotted lines and add a small legend to further clarify.
Q5: Section 5.4
I’m not sure what the overall point of section 5.4 is. It seems very obvious that judge scores need to go up during training. I’m not sure why it really matters that output perplexity is going down, or why it is presented in this way rather than say a line plot with training step on the x axis.
As shown by Beyer et al. [2], increasing harmfulness throughout optimization is not guaranteed and most attacks do not increase harmfulness during optimization. Even GCG, which initially improves harmfulness (Figure 6 in the cited work), eventually saturates near the non-refusal threshold, whereas IHO continues shifting the distribution toward more harmful responses. This is important for estimating worst-case model robustness, as discussed in Section 2 (H.1). Lastly, there is clear connection between being low perplexity (in input and output) and being harmful as shown by the high harm regions. A line plot of perplexity and/or harm (y-axis) over time (x-axis) would have failed to show how closely linked they are. Moreover, several existing methods explicitly optimize for low-perplexity attacks [3, 4], partly to evade perplexity-based defenses. IHO achieves decreasing perplexity without explicitly optimizing for it, suggesting that it would 'accidentally' evade such defenses as a byproduct of the DPO optimization.
Action: We will highlight the importance of optimization and perplexity in section 5.4.
Q6: Transfer with weaker model beats direct optimization
The most interesting section is 5.5 but only warrants 2 short paragraphs. I would like more analysis here. Why does training on Qwen work better
The stronger performance of the Qwen-trained policy is consistent with findings in related work [5], where training against weaker models has similarly been shown to improve attack effectiveness. The exact mechanism is an open research problem and slightly out of scope for this paper. The most likely explanation is that denser rewards simply enable more effective attacker training.
We thank the reviewer for the time invested in reviewing our work and providing feedback.
W1: Novelty
We agree that the discussed desiderata are not completely novel and acknowledge that our method combines existing ideas. However, a) achieving all six simultaneously is essential for a universally usable method and b) despite being standard considerations, no existing method has managed to satisfy all six simultaneously. We discuss the tradeoffs of many existing options in more detail within the paper. Thus, to the best of our knowledge, the combination of diffusion LLM attacker and offline DPO training makes IHO the first openly available method to achieve them at the same time, which we consider our main contribution. AutoAttack is a good example of a simple (low novelty) method that had positive impact on the field by fulfilling all important attack criteria while providing an easy to use open-source implementation [6].
W2: Ablations and Baselines
Regarding the suggested baselines, we cannot compare fairly with them, as we could locate neither code nor checkpoints for either attacker. Moreover, DC-GRPO is primarily concerned with credit assignment in a multi-turn setup. We agree that AdvGRPO would be a desirable baseline, but we cannot guarantee within the limited time of this rebuttal that a reimplementation from the paper would not introduce critical mistakes. We therefore keep JR1 as our primary reproducible RL baseline and added Jailbreak-Zero (JB0) as another more recent PO baseline. Please see our response to Reviewer 9JsQ (W1).
Regarding ablations for classifier-defended models: if we understand the question correctly, App. I.3 already contains one such comparison, namely training against the full pipeline versus training against the undefended model and transferring the policy (held-out ASR(512, 0.8), Fig. 20): on CB+D, 0.57 vs. 0.55; on Qwen-2.5-7B+D, 0.65 vs. 0.60. We are happy to add further variants if the reviewer had a different setup in mind.
Action: We added the Jailbreak-Zero results to the paper.