- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper studies when and how often to apply a training-time defense against clean-label data poisoning. It uses a bound on the one-step change in adversarial loss to motivate concentrating defense interventions in a squared-mass learning-rate (SMLR) window, where much of the schedule’s cumulative squared learning rate lies. The paper also classifies defense policies according to whether their activation decisions use the current gradient state. Using a clipping-and-noising defense against the Witches’ Brew attack, it compares always-on, random, oracle, and window-based policies across several image-classification settings. The experiments report that sparse interventions, particularly within the SMLR window, can often prevent the attack with less clean-accuracy loss than applying the defense at every training step.
Critical strengths
Focusing on the learning-rate schedule and the timing of defense interventions offers a novel perspective on training-time defenses.
Critical weaknesses
The writing is poor and frequently confusing. Many symbols appear without formal definitions at the point where they are used. For example, at the bottom of page 3, the authors write without defining . The roles of , , and are also not clearly specified there. In Eq. (2), depends on , but this dependence is not explicit on the right-hand side. Although the text calls a fixed poison, it does not formally specify whether it denotes perturbations to individual samples, the resulting poisoned dataset, or how it enters .
My second and more serious concern is the soundness and logic of the paper’s central finding. The focus on is motivated by Proposition 1: its left-hand side measures the expected one-step change in adversarial loss, while a positive term proportional to appears on the right-hand side. It is reasonable that defending at different training steps may have different effects, but what this proposition actually says about those effects remains unclear. I take the authors’ intended intuition to be that defending at steps with larger makes larger. However, Eq. (5) accumulates only the positive term from an upper bound. Making that term larger merely loosens the bound. It does not guarantee that the actual adversarial loss increases or that the attack fails. Moreover, the first two terms in Proposition 1 also depend on the learning rate and may change under different defense policies. The authors do not explain why these terms can be set aside while the third term determines the scheduling rule. Finally, even if the analysis established a higher adversarial loss, it is unclear why the learner should prioritize it over its own objective, . Increasing adversarial loss is not the same as minimizing the learner’s training loss. Due to the poor explanation, it is not even clear when Eq. (5) is first presented whether the authors intend the squared learning-rate mass to be increased or decreased. As a result, the theoretical justification for the paper’s central claim is fundamentally unsound.
Questions for authors
See weakness.