- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This manuscript studies how sensitive value estimates are in latent world-model planning. It proposes a white-box attack on the latent state and a black-box attack on observations. Both aim at disrupting trajectory selection, along with a training-free defense that scores candidate trajectories using perturbed-return statistics and action smoothness. Experiments over 50 Meta-World tasks report attack effectiveness, defense performance, and what each scoring term contributes.
Critical strengths
S1. The paper studies a real vulnerability in world-model planning, and it pairs attack design with a matching test-time defense. S2. The experiments span 50 tasks and includes component ablations, so there is some evidence for how the proposed approach behaves.
Critical weaknesses
W1. It seems that both the methodological novelty and the conceptual consistency are unestablished. I could not tell how this differs from prior relevant studies, nor whether the mechanisms as described match what was actually implemented. W2. The experimental results does not carry the weight of the central claims. The reported metrics are inconsistent with each other, the diagnostic results are ambiguous, and the attacker is not trained under equal settings across experiments.
Questions for authors
- The proposed method is not clearly distinguished from existing work on planner overfitting, perturbation-based evaluation, and conservative trajectory scoring.
- Some entries in Table 1 do not add up under the paired-episode ASR of Equation (7). For undefended TD-MPC2-48M under white-box attack, 86.1% clean success and 81.6% ASR together require at least 15.8% of episodes to still succeed, yet the reported attacked success is 12.4%.
- Figure 1 does not support the interpretation the paper draws from it. In panel (b), both groups show a negative prediction-minus-environment return gap, which points to underestimation, not the claimed overestimation — unless the sign or the return comparison is wrong. Panel (c) shows increased sensitivity in only 54% of tasks, with substantial overlap between the clean and poisoned evaluations.
- The black-box objective in Equation (4) targets action matching. That is not the same as valuation instability, nor as reversing the trajectory ranking.
- The abstract, Section 4, the conclusion, and Appendix C all speak of a variance penalty, while Equation (6) and the sensitivity definition use standard deviation.
- Appendix A trains the standalone white-box attacker for 3,000 steps with 10,000 environment steps, but the defense experiments use only 500 attack-training steps and 1,000 warm-up steps. The defense improvement reported there may therefore be partly due to a weaker attacker rather than to the defense itself.