- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
The paper studies the stability of safety refusals in embodied VLM planners under ordinary environmental changes. It introduces task malleability, defined as how easily a previously refused task becomes compliant after inserting an everyday object into the scene. On 846 initially refused tasks, the authors find that 20.2% can be flipped by at least one object, and that random objects are nearly as effective as task-targeted ones. They further analyze which tasks are most malleable, introduce the LatentHarm dataset, and show that signals from a small open-source VLM can predict malleable tasks before querying the target planner. 44707_Refusals_That_Bend_Measu
Critical strengths
-
The paper identifies a clear and practically relevant safety failure mode. The notion of task malleability captures an important question that is not well covered by standard red-teaming or fixed-scene safety benchmarks: whether a refusal remains stable after ordinary environmental changes. The finding that 20.2% of initially refused tasks can be flipped by adding a single everyday object makes this concern concrete and consequential.
-
The empirical study is careful and reasonably comprehensive. The paper goes beyond reporting bypass rates by controlling for decoding noise, comparing targeted, scene-only, and random object insertions, auditing edit fidelity, and analyzing which tasks are most susceptible. This makes the main phenomenon more convincing and provides a stronger basis for the paper’s conclusions.
Critical weaknesses
-
Limited validation across target planners. The core findings are demonstrated on a single target planner, Gemini Robotics-ER 2, with one safety constitution. It is therefore unclear whether the observed malleability generalizes to other embodied VLM planners or alignment mechanisms.
-
The environmental perturbations are synthetic. The study inserts objects using a diffusion-based image editor rather than physically modifying real environments. Although the authors carefully audit edit quality, it remains uncertain whether the same refusal reversals would occur under real physical scene changes.
-
The claim that malleability is a property of the task may be too strong. The experiments show that variation across tasks is much larger than variation across object-selection strategies, but this does not fully establish that object identity is unimportant. A more cautious conclusion would be that task-level susceptibility dominates under the tested object distributions.
-
The predictor lacks external generalization validation. The malleability predictor is evaluated through cross-validation on the same 846-task population, while LatentHarm is constructed from the patterns discovered in this study. Cross-dataset and cross-planner validation would be needed to support stronger claims about deployment-time prediction.
Questions for authors
-
Generality. Do the authors have evidence that both the malleability phenomenon and the proposed predictor generalize to other embodied VLM planners, safety-alignment schemes, or independent datasets?
-
Task vs. object effect. Can the authors quantify how much of the observed variation comes from the task itself versus the inserted object?
In general, I like the idea of this paper. Strong answers to the above questions, particularly with additional supporting evidence, could increase my score.
4 comments
We have completed the experiments described in our initial response. The results are summarized below and will be included in the revised paper.
Generality. We added three additional planners: GPT-5.4, a general-purpose VLM, and Cosmos-Reason2 and RoboBrain2.5, two open-weight 8B models built for robotic planning. Each is evaluated with the same pipeline as in the paper. We first report how many tasks each planner initially refuses, and then how many of those are malleable, meaning that at least one of the 20 variants with an inserted object yields a plan. Mean malleability is the average number of the 20 proposed objects that flip the refusal, over the malleable tasks.
| Planner | Initially refused | Malleable | Mean malleability |
|---|---|---|---|
| Gemini Robotics-ER 2 | 846 | 20.21% (171) | 28.3% |
| GPT-5.4 | 962 | 20.17% (194) | 28.0% |
| Cosmos-Reason2 | 111 | 83.78% (93) | 48.0% |
| RoboBrain2.5 | 154 | 90.91% (140) | 55.6% |
GPT-5.4 behaves like Gemini Robotics-ER 2: it refuses a similar number of tasks, a similar share of them is malleable, and a malleable task is bypassed by 28% of its objects on average on both. The two open-weight planners refuse far fewer tasks, most of what they refuse is malleable, and a malleable task is bypassed by about half of its objects. We attribute this partly to their smaller size.
We then check that the reversals are not decoding noise. Each refused task is queried again on its unmodified image. For each task we compute two rates: the share of its 20 object variants that yield a plan (Object), and the share of its clean re-queries that yield a plan (Re-query). The table reports the average of each rate over the refused tasks with a conclusive answer under both, so tasks that never flip count as zero. The difference is paired within task, in percentage points with its 95% CI, and gives how much more likely a refused task is to yield a plan with an inserted object than when simply asked again.
| Planner | Object | Re-query | Difference (pp), 95% CI |
|---|---|---|---|
| Gemini Robotics-ER 2 | 5.68% | 0.24% | 5.44 [4.37, 6.50] |
| GPT-5.4 | 5.59% | 4.75% | 0.85 [-0.33, 2.02] |
| Cosmos-Reason2 | 40.67% | 33.02% | 7.65 [0.62, 14.67] |
| RoboBrain2.5 | 50.86% | 38.24% | 12.63 [5.95, 19.30] |
Refusals are unstable on every planner. A refused task can yield a plan when the same query is simply repeated, and a visual change to the image, such as inserting an object, makes the reversal more frequent on three of the four planners. On GPT-5.4 the trend is observed, but the difference from the re-query is not distinguishable from zero.
Proxy predictor on a different target family. The predictor's signals come from a small local model and never use the target, so they are identical for every planner. We took the composite (A5) fitted on Gemini Robotics-ER 2 and applied it to GPT-5.4 without refitting, feature selection or recalibration. Because 801 of the 956 tasks that GPT-5.4 refuses are also refused by Gemini Robotics-ER 2, and were therefore fitting tasks for the composite with different labels, we also report the 155 tasks that Gemini Robotics-ER 2 accepts, which the composite has never seen.
| Composite (A5) | Gemini Robotics-ER 2 | GPT-5.4 | GPT-5.4, tasks not refused by Gemini Robotics-ER 2 |
|---|---|---|---|
| Refused tasks | 846 | 956 | 155 |
| Chance level of PR-AUC | 20.2% | 20.3% | 68.4% |
| Spearman ρ | 0.401 | 0.436 | 0.287 |
| ROC-AUC | 0.785 | 0.810 | 0.662 |
| PR-AUC | 0.476 | 0.505 | 0.782 |
| Precision at 50 | 0.58 | 0.64 | 0.76 |
On every metric the paper uses, the predictor performs at least as well on GPT-5.4 as on the planner it was fitted on. On the tasks it has never seen it still ranks malleable tasks above robust ones well above chance.
Task versus object effect. Section 4.3 gives us the data to quantify this. For each of the 192 tasks in that sample we chose the object in three ways (targeted, scene-only, random), 20 objects each, giving 576 bypass rates. We split the variation in these rates with a standard analysis of variance. Each task gets a center, its bypass rate over all 60 of its edits. The object effect is how far a task's targeted, scene-only, and random rates sit from its center. The task effect is how far each task's center sits from the center of all tasks. Squaring these distances and adding them up gives one number for each effect. The task's number is 92% of the two combined and the object's is 8%. The task therefore sets the bypass rate and the object barely moves it. We will add this analysis to Section 4.3 as the answer to this question and make Figure 2 easier to read. The null-edit control reported to Reviewer btta points the same way, an edit that adds no object reverses refusals about as often as one that does.
We thank the reviewer for their valuable feedback. We hope our rebuttal has adequately addressed the concerns raised in the original review. As the discussion period is approaching its end, we would appreciate hearing whether our responses have resolved your main concerns or if any questions or feedback remain.
Thank you for the additional experiments. They address most of my concerns and strengthen the paper. I raise my score to 3.
We thank the reviewer for the encouraging feedback and for stating clearly what would strengthen the paper. We address both questions below.
Generality. We will evaluate additional target planners from different model families (two to three depending on time allowance). For each planner, we will run the same pipeline as in the paper: collect the tasks it initially refuses, insert the proposed objects, and measure how often the refusal is reversed, compared against a clean re-query of the unmodified image. We will also investigate how much of the malleable tasks are shared between the different planners.
Task versus object effect. Section 4.3 (RQ2) answers this by comparing three ways of choosing the object for the same task: targeted, scene-only and random. Figure 2 groups tasks by their reversal rate under targeted objects, so the rise of the targeted bars is by construction. The scene-only and random bars played no part in the grouping, yet they match the targeted bar in every group and rise from under 1% to about 50%. We will revise the text to better quantify and explain this.