- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes PACE, a persistent adversarial attack framework for recurrent visual agents. It first constructs a low-dimensional adversarial basis from critic-guided perturbations using SVD. During online interaction, the attack coefficients are initialized from their previous values, refined using current-observation gradients, and smoothed through an exponential moving average before being projected onto the valid perturbation set. The proposed framework aims to preserve useful adversarial information across consecutive observations while maintaining attack effectiveness and temporal consistency. Experiments on DreamerV3 across DMC Walker Walk, Atari Pong, and Crafter compare PACE with five existing attack methods.
Critical strengths
-
This is a meaningful problem formulation for recurrent visual agents. The paper investigates an important aspect of adversarial robustness by explicitly considering the persistence of attack information across sequential observations. This perspective is relevant to recurrent world-model agents, where current decisions depend on accumulated historical context.
-
PACE achieves competitive reward reductions on DMC Walker Walk, Atari Pong, and Crafter (Tables 1, 2 and Table 5). In particular, it obtains an 85.71% reward drop on Pong while maintaining substantially lower temporal variation than several competing attacks.
Critical weaknesses
-
The proposed framework primarily combines current techniques, including SVD-based adversarial subspace construction, warm-started gradient optimization, and exponential moving average smoothing. Although applying these techniques to recurrent visual agents is maybe reasonable, PACE does not introduce a substantially new optimization objective or mechanism that explicitly models long-term recurrent state dynamics. This is not very interesting to some extent. Because the temporal persistence is mainly implemented by reusing previous attack coefficients and applying standard EMA smoothing. Consequently, the technical contribution seems largely incremental compared with conventional low-dimensional adversarial optimization.
-
The paper emphasizes maintaining attack optimization states across consecutive observations as its central contribution (Lines177–194). However, the ablation studies Table3 and table4 do not independently evaluate this mechanism. Specifically, V3 removes EMA while retaining warm-started optimization, whereas V2 simultaneously removes the subspace constraint and temporal smoothing. There is no experiment that directly compares PACE with independently initialized frame-wise optimization using the same critic-guided basis and optimization budget. Therefore, the reported improvements cannot be clearly attributed to persistent coefficient evolution, leaving the central methodological claim insufficiently validated.
Questions for authors
-
What are the fundamental technical differences between PACE and conventional warm-started adversarial optimization in a fixed low-dimensional subspace? Could the authors clarify which component constitutes the primary algorithmic innovation beyond combining existing techniques?
-
Could the authors provide a controlled ablation that removes coefficient warm-starting while preserving the critic-guided basis and online optimization budget? This would help determine whether maintaining the previous attack state provides an independent performance advantage.