- Rating
- 4
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper focuses on the creation of backdoor or poisoned examples. It makes the observation that classic ways of creating backdoor samples result in ones that lie off the data manifold and are hence potentially vulnerable to detect via geometric measures. Leveraging this observation they proposed a new method to create on maniold backdoor examples that are harder to detect.
Critical strengths
-makes an intriguing observation that conventional backdoor samples are geometrically vulnerable to detection, opening the door to manifold manipulation techniques to improve stealthiness
-new loss function proposed to keep backdoor samples on manifold follows logically from collection of evidence and step by step observations
-experimental results are strong
Critical weaknesses
-proposed new loss function requires two hyperparameters – it is not clear how to choose these and how sensitive resulting behaviour is – please elaborate
Questions for authors
-the geometric measures (k-nn distance, DAO score) are estimates of population quantities. Are any of the conclusions in the paper affected by estimation error for these geometric measures? -does the use of pca in formulating the revised loss function eq 5 mean there is an implied “linearity” assumption?
3 comments
Please engage in the discussion with authors
Dear Reviewer 5xDM,
Please engage in the discussion with authors, thank you!
AC
Thankyou, acknowledging your response.
Response to Reviewer 5xDM (2/2)
(Part 2/2)
The results show three points:
We also bootstrapped the query samples at N=2,048 to measure the query-side sampling error: the half-width of the 95% confidence interval of AUROC is at most 0.01 for cross-modal attacks and at most 0.06 for OMA and MSE, both much smaller than the gap between the two groups.
3. Whether using PCA in Eq. (5) implies a "linear" assumption (Question 2)
You raised the concern:
No. We implement the normal loss with PCA decomposition because it is simpler to implement. PCA is a commonly used technique in machine learning: it has a closed-form solution and requires few design choices, which benefits reproducibility and interpretability. This choice is common in the deep learning literature [1, 2], and it is not meant to assume that the representation space has any linear structure.
In fact, in Section 5 of the original paper (Anchoring to populated target regions), we also explained why we did not use non-linear distribution matching:
An exact non-linear distribution-matching loss would have to estimate a high-dimensional distribution from only 500 poisoned pairs (a 0.1% poisoning rate), which is highly unreliable, whereas the PCA-based normal loss works well with the few poisoned samples available. The PCA subspace is only a coarse approximation of the clean support. It retains 95% of the target-class variance, so even if the clean manifold is curved, the subspace approximately contains it. Penalizing the component outside this subspace is therefore a necessary condition for being on-manifold, not an assumption that the manifold is flat.
We hope the above clarifications address your questions.
[1] Haoyu Ma, Xiangru Lin, Yizhou Yu. I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation. TPAMI, 2024.
[2] Luo et al. Robust Graph Condensation via Classification Complexity Mitigation. NeurIPS, 2025.