- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
In this paper, the author studied the practical problem in sparse adversarial attacks, where the choice of sparsity coefficient controls the balance between ASR and density. Instead of predetermining the sparsity coefficient, the authors propose Density Feedback Control (DFC), which tightens or relaxes this coefficient at the end of each epoch according to the gap between the observed hard-mask density and the target, without changing the generator architecture or loss. Experiments demonstrate that DFC can be considered a plug-in component to improve the performance of existing methods.
Critical strengths
- This paper studied a practical problem in sparse adversarial attacks. The choice of sparsity coefficient is important in controlling the balance between ASR and density.
- The proposed DFC methods can be considered as a plug-in component to improve the performance of existing methods. Experiments also demonstrate its success under most of the scenarios.
Critical weaknesses
- Lack of technical contribution, as the proposed DFC is essentially a constrained error-feedback update with momentum.
- More experiments should be conducted to demonstrate the generality of the proposed method, and the ablation study lacks a control variable.
Questions for authors
-
Applying existing concepts of regularization-based feedback control to generator-based sparse adversarial attacks could be valuable. However, for a venue like ICLR, it is essential to provide a technical contribution. As it stands, I do not see any novel control theory, stability analysis, convergence guarantees, or control mechanisms specifically designed to enhance adversarial transferability. The author should further justify the technical contribution and novelty of this paper.
-
In Figure 4, the authors compare and . It can be observed that the average ASR across the ten target models remains nearly identical. In other words, completely removing the momentum term results in almost no drop in ASR. This further undermines the necessity of the specific damped controller design. I will ask the authors to provide a clear answer: what, precisely, are the unique technical contributions of the DFC approach that cannot be achieved through a standard Lagrangian multiplier update?
-
There are two additional confounding factors in the experimental section. First, the number of warm-up epochs is inconsistent. The original method employs 3 warm-up epochs, whereas DFC uses 2. Second, the initial value for TSAA has been modified. The original TSAA reduction/stabilization uses , while the initial in DFC is set to . The authors explain that this adjustment is necessary because a larger coefficient would cause the density to drop to zero following the warm-up phase. However, this also implies that DFC and the baseline differ not only in their control strategies but also in their initial regularization strength.
-
In the experiment, the full text only tests . It is necessary to show the performance under different , because the dynamic behavior at different target densities can be entirely different.
-
Furthermore, the author claims that all three methods can achieve a mean density within ±1 percentage point of the target. However, as shown in Table 1, the original TSAA and EGS-TSSA already meet this ±1 pp criterion. Incorporating DFC into EGS-TSSA actually causes the result to deviate further from the target. Therefore, the current experimental results only support the conclusion that DFC provides better density tracking performance for this specific target.