- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes a model-level backdoor detection method that aims to generalize across unseen backdoor attacks. The key motivation is that existing meta-classifier-based methods often capture attack-specific features, leading to poor cross-attack generalization. To address this, the authors propose class-wise decision-space probing, which extracts representations from the final classification layer by optimizing a feature vector for each class. These representations are then fed into a meta-classifier to distinguish clean and backdoored models. Experiments across 12 backdoor attacks demonstrate strong cross-attack generalization, achieving an average AUC of 0.966. However, the method relies heavily on the final classification layer and can be bypassed by adaptive attacks that leave this layer unchanged.
Critical strengths
-
Addresses the important problem of cross-attack generalization in backdoor detection.
-
A simple and effective method with strong experimental results across 12 attacks and multiple architectures.
-
Includes useful ablation studies and adaptive attack evaluations.
Critical weaknesses
-
Insufficient explanation of why the proposed representation improves cross-attack generalization.
-
Important experimental details, such as the number of training and testing models in Table 1, are unclear.
-
Vulnerable to adaptive attacks that freeze the final classification layer.
Questions for authors
Thank you for submitting the interesting work to ICLR 2027. I still have a few concerns.
-
Limited utilization of backdoor-related information. Prior studies have shown that backdoor-related behaviors can be encoded in feature extraction layers, and techniques such as convolutional layer pruning can effectively mitigate backdoors. However, this paper focuses only on the final classification layer, potentially discarding substantial backdoor-related information from earlier layers. It is unclear whether the improved efficiency justifies this information loss. The authors should provide stronger motivation for this design choice and investigate whether incorporating features from earlier layers could further improve detection robustness.
-
Limited experimental evaluation. The experimental evaluation is not sufficiently comprehensive. Although multiple architectures are considered, the experiments are mainly restricted to relatively small CNN-based image classifiers. Evaluations on more diverse and modern architectures, such as Vision Transformers, would strengthen the paper's claims about generalizability.
-
Insufficient experimental details. Several important experimental settings are unclear, particularly the number of clean and backdoored models used for training and testing in Table 1, as well as how these models are split. These details are essential for assessing the reliability and reproducibility of the reported results.
4 comments
Model counts and training/evaluation splits.
We have expanded the experimental details to specify the model pools and detector-training protocol. For each ten-class configuration, the standard pool contains 256 clean models and 1,830 backdoored models. Each of the twelve attacks contributes 100 class-agnostic models. BadNets, Blended, BPP, Filter, LF, Refool, and SSBA additionally contribute 90 class-specific models each, giving 1,200 class-agnostic and 630 class-specific backdoored models.
For the full GTSRB configuration, the pool contains 256 clean models and 3,240 backdoored models: 172 class-agnostic models per attack and 168 class-specific models for each of the seven applicable attacks. For CIFAR-100, the pool contains 100 clean models and 943 backdoored models: 50 class-agnostic models per attack and 49 class-specific models for each of those seven attacks. Across the six main configurations, this gives 1,380 clean and 11,503 backdoored models, totaling 12,883 models.
All compared methods use the same sampling procedure, with a sampling ratio of and sampling without replacement. For source attacks containing both backdoor subtypes, we sample from each subtype a number equal to of the smaller subtype pool, rounded down, and construct the detector-training set with a clean:class-agnostic:class-specific ratio of . For attacks containing only one subtype, we sample of that pool and an equal number of clean models. For example, on CIFAR-10/ResNet-18, a BadNets detector uses 54 clean, 27 class-agnostic, and 27 class-specific models, totaling 108 training models. An LC detector uses 30 clean and 30 backdoored models, totaling 60.
All models used for detector training are excluded from evaluation. Source-attack evaluation uses the remaining clean and source-attack models. Cross-attack evaluation uses the same held-out clean models and all models from the corresponding non-source attack, without further subsampling or balancing.
The model-generation settings and sampling protocol are detailed in Appendix B.1 and B.2.
Hi,
Thanks for your detailed rebuttal. I tend to keep my current rating.
Dear reviewer, Do you have any remaining concerns that we can address? We’d be happy to continue the discussion.
We thank you for your careful review and for recognizing the importance of cross-attack detection, the effectiveness of our method, and the useful ablation studies. In response to your comments, we have clarified the probing scope and the default choice of the final classifier, added a ViT-B/16 evaluation, and specified the model counts and training/evaluation splits. We hope these additions address your concerns and respectfully ask you to consider raising your score in light of the new evidence.
Q1: Incorporating earlier-layer information and motivating the default probing location.
Thank you for highlighting the importance of backdoor-related information in earlier layers. We have clarified that our framework supports probing a continuous classification subnetwork extending from a selected intermediate location to the output. All parameters within this subnetwork remain fixed, while its input features are optimized separately for each class. Choosing an earlier probing location changes the subnetwork and its input shape, while retaining the same class-wise optimization and representation construction procedure.
The final classifier is our default based on the layer-wise comparison of detection performance and computational cost. On CIFAR-10/ResNet-18, using a common budget of 1,000 steps per class, FC-only probing achieves an AUC of 0.964 in 8.56 seconds. Including the last residual block improves AUC to 0.983 but increases the cost to 31.03 seconds. These results show that incorporating earlier-layer information can improve detection, while extending the probing scope increases computational cost. We therefore recommend the final classifier as the default choice balancing effectiveness and efficiency, while retaining the flexibility to probe from earlier intermediate locations.
The frozen-suffix experiment directly investigates whether earlier-layer information improves robustness. When the attacker freezes only FC, the backdoored models retain an ASR of 93.83, while FC-only detection yields an AUC of 0.266. Extending probing to B4.2 and B4.1 raises AUC to 0.744 and 1.000, respectively.
These results establish an experimentally supported choice: FC-only probing provides an efficient default for the standard cross-attack setting, while the same framework can incorporate earlier-layer information to improve detection against attacks that deliberately preserve the final classifier. We have clarified this flexibility and the associated computational trade-off in the revised manuscript.
Q2: Evaluation beyond CNN architectures.
Following your suggestion, we added an evaluation on ViT-B/16 with CIFAR-10, reported in Appendix C.4. We use a pretrained ViT-B/16 with a ten-class classification head and fine-tune 20 clean models and 20 BadNets models. The backdoored models use a 10 poisoning ratio and cover all ten target classes with two random seeds per target class.
We apply the same class-wise probing procedure to the final linear head. Its input dimension is 768, producing a 10×768 representation. Probing uses the same all-ones initialization and 20,000 Adam steps per class, and detection uses the same 1D-CNN meta-classifier design and training procedure.
We sample six clean and six backdoored models without replacement for detector training. Evaluation uses only the remaining 14 clean and 14 backdoored models, with no overlap between detector training and evaluation. The detector achieves an AUC of 1.000 on these held-out models.
This experiment demonstrates that the probing procedure and meta-classifier design also support effective backdoor detection on a pretrained transformer architecture, extending the architectural evidence beyond the CNN-based configurations in the main evaluation.