- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces UAPCore, a data-efficient framework for computing universal adversarial perturbations (UAPs) for tabular classifiers. The main observation is that, during UAP optimization, the victim classifier remains frozen, and therefore its penultimate-layer representation is stationary. The authors exploit this property by selecting a representative coreset once, before attack optimization, and computing all subsequent gradient updates only on this subset.
The proposed framework selects samples in the frozen feature space using k-Center, Facility Location, or random sampling, and then applies standard FGSM or PGD-based UAP optimization on the selected subset. The method is evaluated on 44 OpenML tabular classification datasets. Using only 10% of the training data, k-Center-based UAPCore recovers the full-data fooling rate within two percentage points on a large fraction of datasets while providing a median wall-clock speedup of approximately 8.5$\times$ for PGD. The authors additionally study different coreset ratios and perturbation budgets and evaluate transfer of MLP-crafted perturbations to XGBoost, TabNet, and FT-Transformer models.
The paper presents a simple and practically useful way to reduce the computational cost of existing gradient-based UAP methods rather than introducing a fundamentally new adversarial attack.
Critical strengths
-
The paper identifies a simple but useful structural property of UAP optimization. Since the victim model is frozen, the representation used for sample selection does not evolve during optimization. This allows the coreset to be selected only once rather than repeatedly recomputed, making the approach considerably cheaper than standard coreset-based training procedures.
-
The empirical evaluation is reasonably broad within the tabular setting. The authors evaluate 44 datasets, multiple perturbation budgets, FGSM and PGD, several coreset sizes, different selection strategies, and cross-architecture transfer. In particular, obtaining approximately 8.5$\times$ median PGD speedup with a 10% coreset while maintaining near-full-data fooling rates demonstrates that the approach can provide a meaningful practical benefit.
Critical weaknesses
-
The central proxy underlying UAPCore is not directly validated. The method selects examples according to geometric coverage in the frozen penultimate feature space, with the intuition that this captures redundant optimization signals. However, the UAP update is determined by gradients, and the paper itself acknowledges that nearby feature representations do not necessarily imply similar gradients. A quantitative analysis relating feature-space similarity to gradient similarity or gradient alignment would substantially strengthen the methodological justification.
-
The experimental comparison and scalability evidence are somewhat limited relative to the claims. The main baselines are full-data UAP optimization, random subset selection, k-Center, and Facility Location. Although related gradient-aware coreset approaches such as CRAIG and GradMatch are discussed, there is no empirical comparison with an adapted gradient-aware subset selection baseline. Moreover, all evaluated datasets contain only 500-2,500 examples. This is particularly relevant because exact k-Center has a quadratic selection component, and the authors themselves note that its computational advantage can eventually disappear for sufficiently large datasets. Consequently, the current experiments do not fully establish scalability in the larger-data regime that motivates the method.
Questions for authors
-
Can the authors directly validate the main feature-space proxy? For example, across samples or local neighborhoods, how strongly does distance in the penultimate representation correlate with cosine similarity or alignment between the corresponding UAP gradients? A strong relationship would substantially strengthen the explanation for why a fixed geometric coreset preserves the optimization trajectory.
-
Have the authors considered a gradient-aware subset selection baseline, for example an adaptation of GradMatch, CRAIG, or direct gradient clustering/matching? If such approaches are computationally impractical in this setting, it would be useful to quantify that cost. This comparison would help determine whether the benefit comes specifically from frozen feature geometry or more generally from selecting informative subsets.
-
How does the end-to-end speedup behave on substantially larger datasets, for example tens or hundreds of thousands of samples? Since exact k-Center introduces an component, evidence using the proposed approximate variant or larger-scale datasets would materially affect my confidence in the scalability motivation.
2 comments
I thank the authors for their detailed response.
The validation of the feature-space proxy indeed makes the contribution of the paper much clearer now, i would also suggest highlighting it on the main paper.
I'll read everything carefully with the revised updated version, and ill reconsider my assessment accordingly.
Response to Reviewer TANc
We thank the reviewer for a careful and accurate summary, and for recognizing the one-shot selection property and the breadth of the evaluation. We address the three questions below.
Q1 / W1: Directly validating the feature-space proxy. We agree that this is the central question. As stated in Sec. 3.1, the paper does not assume that feature proximity implies gradient similarity. It treats feature geometry as a proxy and evaluates it by its end result, fooling-rate fidelity.
We have one supporting diagnostic, which we will add to the appendix. It measures the cosine similarity at epoch 0 between the mean gradient on the k-Center coreset and the mean gradient on the full training set (PGD, ε=0.10, ρ=0.10):
This indicates that gradient alignment is what mediates fidelity, and that the coreset selected from frozen feature geometry attains high alignment on most datasets.
Q2 / W2a: Gradient-aware baselines. The goal of UAPCore is to select the right samples once, which the frozen victim makes possible. Our Facility Location strategy (C2) is CRAIG's facility-location selection rule, applied in this one-shot setting. CRAIG and GradMatch re-select periodically because, in training, the model and therefore the gradients change. Each re-selection would cost a full-data gradient pass, which is exactly the per-epoch cost UAPCore is designed to remove. Iterative re-selection is therefore outside the setting we study. We will make the relation to CRAIG explicit in Sec. 3.2.
On whether the benefit comes from frozen feature geometry or from informative subsets in general, the existing comparisons separate the two:
Q3 / W2b: Scalability to tens or hundreds of thousands of samples. We agree this is the main open question, and we will state it more prominently as a limitation. Three points in the paper bear on it:
We thank the reviewer again for questions that will sharpen the paper.