- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper proposes Triangular Consistency (TC), a consistency-regularization method for adversarial training. The main idea is to jointly enforce within-branch consistency between each clean view and its corresponding adversarial example, and cross-branch consistency between adversarial examples generated from different augmented views. The resulting objective combines three Jensen--Shannon divergence terms, , , and . The authors provide theoretical analyses involving robust generalization, prediction stability, and local curvature. Experiments on CIFAR-10 and CIFAR-100 show improvements over several adversarial training baselines under PGD attacks, with additional results on larger perturbation budgets and non- attacks.
Critical strengths
-
The proposed triangular consistency objective is intuitive and easy to integrate into existing adversarial training frameworks without additional network modules. Jointly considering within-branch and cross-branch consistency is a reasonable direction.
-
The experiments cover different architectures and attack methods on CIFAR-10 and CIFAR-100. TC achieves improvements under PGD and CW attacks, while the results on StAdv suggest potential benefits beyond the training threat model.
Critical weaknesses
-
The proof of Theorem 1 in Appendix C appears to contain inconsistencies. Under the stated construction, misclassifies one adversarially perturbed sample, suggesting that its robust training error should be rather than zero. Furthermore, the subsequently introduced classifier does not appear to achieve zero triangular consistency loss under the specified perturbations. These issues raise concerns about the correctness of the theoretical analysis.
-
The role of in the theoretical analysis is unclear. In Eq. (11), the triangular consistency defect only involves and , and the triangle inequality in Eq. (13) also relies solely on these two terms. This suggests that the theoretical argument may only require rather than the full three-edge objective. However, Table 5 does not include this particular two-edge combination, making it difficult to assess whether all three constraints are necessary.
Questions for authors
Q1. Could the authors revisit the proof of Theorem 1? Additionally, could the authors clarify how Eq. (49) in Proposition 3 follows from the Lipschitz assumption? Are further assumptions required?
Q2. In Table 5, the full TC objective improves PGD accuracy but performs worse than the two-edge objective under AutoAttack on both datasets. How should this result be interpreted? Could the authors also provide a comparison in which the effective regularization strengths of the cross-branch and decoy terms are better matched?