- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Fast Preemptive Robustification (FPR), which runs efficiently on commodity CPUs, enabling real-time PR without dedicated GPUs. Regarding the current PR, it remains underexplored and faces several important limitations. First, dependence on well-trained surrogate classifiers limits applicability, as surrogates are task-specific and may even be unavailable in some practical settings. Moreover, the required iterative optimization or dedicated PR generator training incurs substantial costs. Third, the variations generated by existing methods lack human interpretability. FPR exploits the observation of Laplacian response to improve the robustness, and the experimental results show that FPR can achieve better performance.
Critical strengths
- The research problem is interesting. Preemptive robustification (PR) proactively enhances the robustness of input samples before attacks, rather than relying on model training or post-attack defenses. FPR further introduces a more efficient approach to PR.
- The proposed FPR method is simple and computationally efficient, requiring low computational resources.
- The experimental evaluation is broad, covering various attack scenarios and experimental settings.
- The paper is well-written and easy to follow, and the figures are clear and informative.
Critical weaknesses
- The methodological novelty is limited. The proposed method essentially applies an existing technique to PR. Although the research problem is interesting, the novelty of the method itself is not sufficiently compelling.
- The lack of evaluation against adaptive attacks may lead to an overestimation of the robustness improvements. FPR is a deterministic and known image transformation with a very simple formulation. If attackers are aware of its mechanism and parameters, they may develop targeted strategies to undermine its effectiveness, such as explicitly optimizing perturbations that counteract the high-frequency enhancement introduced by FPR.
- The hyperparameter selection may be challenging in practical scenarios. One key parameter of FPR is the sharpening coefficient α, which appears to be related to the desired protection strength and the attack intensity. However, the attack strength and perturbation magnitude are typically unknown in real-world scenarios, making it difficult to determine an appropriate α. The paper only evaluates different values of α but lacks further discussion or analysis of how this parameter should be selected in practice, particularly whether it can be determined adaptively.
- The claimed computational efficiency lacks sufficient experimental validation. Although the paper emphasizes reduced computational costs, it does not provide direct comparisons of computational overhead with existing PR methods.
Questions for authors
See weakness.