- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
TIDE detects clean-label backdoor poisoning through collective training influence, without a known-clean reference set or known poisoning rate. It builds a source–probe influence graph from temporary training and uses greedy peeling to select suspicious samples before retraining. Across CIFAR-10, GTSRB, and additional Tiny ImageNet and VGG experiments, the authors report reduced attack success with generally preserved clean accuracy. For example, CIFAR-10 Narcissus ASR falls from 91.20% to 7.92%, although substantial residual ASR remains for the Wicked variants. The results support a useful cleaning trade-off; the paper interprets shared influence as the detection signal.
Critical strengths
-
Cleaning clean-label poisons without trusted reference data is a meaningful problem: correct labels make suspicious samples harder to identify individually. Section 4's collective source–probe formulation is an interesting extension of existing influence analysis. Its novelty lies in the bipartite detection procedure, rather than introducing influence-based defense itself.
-
Tables 1–2 and Appendix G provide reasonably broad evidence for mitigation across three datasets, two architectures, and five attack configurations. Comparisons include FLARE (2025), with PureGen (2024) in Appendix E. The results support a useful mitigation–accuracy trade-off, although the pairwise attribution and poisoning-specific interpretation require the separate checks discussed below.
Critical weaknesses
-
Equations (4)–(5) distribute the batch's net logit-change magnitude across samples. Opposing sample effects can therefore cancel before attribution and receive zero scores. Cosine weighting also discards feature norms, so relative contributions can be distorted even with a frozen linear head. This limits the claimed pairwise attribution beyond the acknowledged difference from leave-one-out influence.
-
Equation (7)'s poisoning specificity is unresolved. Higher poison-to-poison influence than the other pooled pair means does not ensure that the poisoned block outscores an equally sized benign cohesive block. Appendix A does not separate class or degree effects, and Appendix F's optimizer comparisons cannot validate that identification step.
Questions for authors
-
Under what assumptions do Equations (3)–(5) approximate individual step effects? How are within-batch cancellation, feature norms, and momentum or backbone updates handled?
-
What distinguishes the selected block from a clean, cohesive class or a high-degree source group? Can class-matched clean blocks and marginal rankings be compared using the same influence matrix?
-
At low poisoning rates, how does proportional peeling behave when the probe contains no poison? Please clarify the final partition-aggregation rule and Table 10's stated 0.5% versus implied 5% removal budget.
4 comments
W2 / Q2
To examine the class-effect concern, we extend the analysis of Appendix A (now summarized in the new Section 5.5) by comparing poison-to-poison influence with clean-to-clean influence within the target class. Across all seven evaluated settings (Section 5.5, Table 3; full statistics in Appendix A, Table 4), poison-to-poison pairs have higher mean influence than clean-to-clean pairs both overall and within the target class. Target-class clean pairs also show higher mean influence than clean pairs overall, confirming that a class effect exists, which is why the within-class comparison matters. Nevertheless, the higher mean influence of poison-to-poison pairs persists when the clean comparison is restricted to the target class.
Table R3. Mean (median) pairwise influence; Clean denotes all clean samples, and Clean_t denotes clean samples from the target class.
| Data | Attack | Poison Poison | Clean Clean | Clean_t Clean_t |
|---|---|---|---|---|
| CIFAR-10 | Narcissus | 0.1193 (0.0109) | 0.0053 (0.0026) | 0.0476 (0.0231) |
| CIFAR-10 | COMBAT | 0.6100 (0.5746) | 0.3236 (0.1895) | 0.4380 (0.1239) |
| CIFAR-10 | Wicked-BadNet | 0.7136 (0.1299) | 0.2553 (0.0636) | 0.3655 (0.0893) |
| CIFAR-10 | Wicked-Blended | 0.6881 (0.1305) | 0.3686 (0.0897) | 0.4717 (0.2043) |
| CIFAR-10 | Wicked-SIG | 0.6767 (0.0976) | 0.2324 (0.1047) | 0.2444 (0.0568) |
| Tiny ImageNet | Narcissus | 9.3556 (7.9551) | 7.3762 (5.4336) | 7.5548 (6.1562) |
| Tiny ImageNet | Wicked-BadNet | 8.5550 (5.8516) | 7.5446 (5.4785) | 7.5703 (6.2266) |
Q3
Proportional peeling when the probe contains no poison. Proportional peeling removes samples from the side with the smaller removed fraction, which assumes that poisons are distributed over the source and probe sets, as expected from a random partition. If the probe contains no poison, this assumption does not hold and peeling on the probe side can only remove clean samples. To quantify this effect, we compared our setting with partitions in which all poisons are forced into the source set (so the probe contains no poison), using the same setting as our main experiments, averaged over three runs. With a random probe, TIDE achieves TPR 0.7260 and FPR 0.2597, and with a probe containing no poison, TPR 0.4045 and FPR 0.1744. Detection is therefore weaker when the probe contains no poison, but it does not collapse. We report this analysis in Appendix E.
Aggregation rule. In each repetition, the dataset is randomly partitioned into a source set and a probe set (the probe sets are disjoint across repetitions), and all samples are nodes of the bipartite graph. Greedy peeling yields a suspiciousness ranking over all samples, and the position in this ranking that maximizes the objective defines the selected subset of repetition . We average the rank of each sample over the repetitions to obtain an aggregated ranking, and remove the top-ranked samples up to the average of the per-repetition cutoffs. We have added this rule to Section 4.2 (Multiple Random Partitions).
Table 10 (Table 13 in the revised paper). TIDE does not use a fixed budget. Greedy peeling returns the subsets that maximize the objective . However, integer programming and simulated annealing solve a problem of a given size, so for a fair comparison between these approaches, we fixed the selection size to 5% of the training set for all of them when the poisoning rate is 0.5%. This fixed budget is used only in this comparison. We have corrected the stated selection size to 5% in Appendix G.
Thank you for the clarifications and additional analyses. The within-class comparisons and aggregation details are helpful. However, higher average poison-to-poison influence does not establish that the selection objective distinguishes poisoned blocks from equally sized cohesive clean blocks or high-degree groups. The acknowledged cancellation, feature-norm, and momentum effects also leave the reliability of pairwise attribution insufficiently established. I therefore maintain my original rating.
W1 / Q1
We thank you for your thoughtful review.
Assumptions, momentum, and backbone updates. At each step, we measure the actual change of the probe logits on the complete model (Eq. (2)), so backbone updates are included in the quantity being attributed. Eqs. (3)–(5) then distribute this change among the batch samples using a last-layer, first-order approximation. Each sample’s share is proportional to the similarity of its last-layer feature to the probe’s feature, weighted by its prediction error. We therefore present it as an approximation, not as leave-one-out influence. Since the tracking run uses SGD with momentum (Section 5.1), the measured change also contains a carry-over from earlier batches, which our attribution assigns to the current batch. We regard this as part of the approximation.
Within-batch cancellation. The reviewer is right that the effects of samples in the same batch can cancel before attribution, so those samples receive zero (or very small) scores, since we distribute the batch’s net logit change. This is a limitation of a single step. However, batch composition is randomized across epochs and repetitions, so each sample’s accumulated score reflects its contributions across multiple batch contexts rather than a single batch. Samples that consistently influence the probe in many different batches tend to obtain a larger accumulated score (Eq. (6)), which is what the detection uses. Consistent with this, poison-to-poison pairs have the highest mean accumulated influence in our measurements (Section 5.5, Table 3).
Feature norms. We agree that cosine weighting discards feature norms, so relative contributions can be distorted. We use cosine similarity as a simple, scale-free weighting function. Prediction error contributes to each sample’s attribution weight, while the measured batch-level change determines the total magnitude to be allocated. Other similarity measures (e.g., unnormalized inner products) are possible, and we have added this to the limitations.