- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper is motivated by the inconsistency between surrogate gradients and the actual forward dynamics of hard-spiking neurons. Guided by decision-relevant spike flips, the proposed FARE method adaptively adjusts the parameters of surrogate gradients and combines the original and adjusted surrogate gradients through averaging. Experiments on both small- and large-scale datasets demonstrate the effectiveness of FARE compared with baseline methods using original surrogate gradients.
Critical strengths
S1. The authors clearly demonstrate the inconsistency between surrogate gradients and hard-spike forward dynamics through extensive toy experiments, providing a clear motivation for using spike flips to address this issue.
S2. The experiments are comprehensive, with extensive analyses conducted to evaluate the effectiveness of the proposed method.
Critical weaknesses
W1. It remains unclear why better alignment between surrogate gradients and hard-spike forward dynamics would necessarily improve the adversarial robustness of SNNs. Intuitively, if the surrogate gradients more accurately reflect spike flips during forward propagation, attackers could also exploit these more informative gradients to generate stronger adversarial examples. This concern is also supported by the findings of [1], which demonstrate that improved surrogate-gradient approximations can lead to more effective adversarial attacks.
W2. The ablation studies in Figure 8 show that using only the dynamic response leads to really bad performance, while the main results in Table 1 indicate that using only the original response yields poor adversarial robustness. Surprisingly, simply averaging these two responses results in significant performance improvements. The authors should provide a more detailed explanation of why combining two individually ineffective responses leads to such substantial gains.
[1] Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networks. CVPR 2026.
Questions for authors
Please clarify the Weaknesses part as well as the following question:
Q1. According to the paper, the importance weight is computed using gradients and plays a crucial role in determining (Eq. (13)). However, computing appears to require surrogate gradients, which the authors argue are inconsistent with the actual hard-spike forward dynamics. This raises a concern about whether such potentially inaccurate gradient-based weights can reliably guide the estimation of .
I would be willing to reconsider my rating if all my concerns are adequately addressed.
10 comments
Response to Reviewer 4y1W (part 2/4)
Continuation of our response to Weakness 1
5.3 Gradient Obfuscation Checking
Since Fare directly modifies surrogate gradients, we examine whether its robustness depends on difficulties in gradient-based adversarial search. Following the diagnostics of [2], we assess attack strength, backward-rule dependence, and gradient-free search as follows.
Attack strength and backward access. Figure 4 shows that iterative PGD is more effective than FGSM and white-box attacks outperform transfer-based black-box attacks. PGD accuracy decreases as the perturbation budget increases and approaches zero at large budgets. Figure 5 further shows that replacing the attack backward rule causes no abrupt accuracy collapse while the model remains fixed.
Strengthened white-box search. Table 3 includes multi-restart PGD and APGD-CE/DLR. APGD yields lower accuracy than PGD, motivating per-example aggregation of attack successes across losses and backward rules. Expanding the white-box ensemble from to reduces accuracy by only 0.09-0.50% across all valid configurations. This limited additional reduction suggests that the aggregated search is approaching saturation under the tested budgets.
Gradient-free verification. Furthermore, as shown in Table 3, adding SPSA and Square Attack to reduces accuracy by only 0.03-0.50 percentage points. Increasing the Square query budget from 5000 to 10000 yields a further reduction of 0.01-0.30%. These independent searches identify few additional failures after strengthened white-box evaluation. Taken together, the checks show that Fare does not rely on gradient obfuscation for robustness.
Table 3. Strong-attack evaluation of Fare (%).
| Attack / Ensemble | CIFAR-10 | CIFAR-100 | DVSCIFAR-10 | SeqCIFAR-10 | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Base surrogate | Tri | Sig | Rec | Tri | Sig | Rec | Tri | Sig | Rec | Tri | Sig | Rec |
| 33.89 | 29.91 | 24.75 | 14.07 | 12.82 | 9.25 | 62.90 | 50.00 | N/A | 13.03 | 9.09 | 7.36 | |
| 36.96 | 31.09 | 28.48 | 19.12 | 14.76 | 9.99 | 64.40 | 52.10 | N/A | 15.97 | 12.47 | 8.01 | |
| $PGD-10 \cup SPSA $ | 33.60 | 29.87 | 24.72 | 14.07 | 12.58 | 9.16 | 62.70 | 49.60 | N/A | 13.00 | 8.94 | 7.18 |
| 31.19 | 26.49 | 22.88 | 13.25 | 11.10 | 8.16 | 60.00 | 49.10 | N/A | 11.98 | 8.21 | 6.10 | |
| 31.08 | 26.42 | 22.73 | 13.17 | 10.98 | 8.04 | 59.80 | 49.00 | N/A | 11.74 | 7.97 | 5.99 | |
| 19.24 | 14.58 | 12.04 | 4.02 | 3.76 | 3.10 | 23.50 | 21.70 | N/A | 3.10 | 2.19 | 1.47 | |
| 27.58 | 21.41 | 18.51 | 2.54 | 1.98 | 1.72 | 29.70 | 24.70 | N/A | 2.76 | 1.27 | 0.99 | |
| 18.72 | 14.17 | 11.68 | 2.31 | 1.82 | 1.51 | 22.70 | 20.90 | N/A | 2.51 | 1.12 | 0.83 | |
| 18.25 | 13.77 | 11.27 | 2.17 | 1.64 | 1.36 | 22.30 | 20.40 | N/A | 2.38 | 1.03 | 0.74 | |
| 18.17 | 13.65 | 11.21 | 2.12 | 1.63 | 1.33 | 22.20 | 20.10 | N/A | 2.33 | 0.99 | 0.72 | |
| 18.14 | 13.63 | 11.20 | 2.09 | 1.61 | 1.30 | 21.90 | 19.90 | N/A | 2.29 | 0.97 | 0.70 |
Reference
[2] Athalye, Anish, et al. Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples. ICML, 2018.
Response to Reviewer 4y1W (part 3/4)
Weakness 2: W2. The ablation studies in Figure 8 show that using only the dynamic response leads to really bad performance, while the main results in Table 1 indicate that using only the original response yields poor adversarial robustness. Surprisingly, simply averaging these two responses results in significant performance improvements. The authors should provide a more detailed explanation of why combining two individually ineffective responses leads to such substantial gains.
Response to Weakness 2:
Thanks for asking us to explain this.
First, allow us to clarify, each response is useful, rather than “ineffective”. But they have different limitations. The original response supports strong clean accuracy, while providing limited guidance about perturbation-induced flips. The dynamic response already improves robustness on the non-event datasets. For example, using it alone raises SeqCIFAR-10 PGD accuracy from 0.04% to 9.47%. The severe collapse occurs on DVSCIFAR-10. These results suggest that the two responses support different learning needs, which helps explain their benefit when combined.
Their main advantage is that they compensate for weaknesses at different membrane states. The original response consistently supports learning near the firing threshold. The dynamic response extends sensitivity toward important flip regions, but changing its range can weaken the response in regions needed for ordinary classification. A simple analogy is a learning signal passing through several gates. One response keeps some gates open but leaves others nearly closed, while the other response has a different set of weak gates. Combining them can keep the signal flowing through the whole path. This matters because gradients travel across multiple layers and timesteps, where a weak response at one important point can limit learning along an entire path. The combined response can therefore improve gradient propagation substantially, even though it remains a simple average locally.
Furthermore, at the formula level, you are absolutely right that Fare is “simply averaging these two responses.” However, this operation happens at each neuron during training, rather than after two models have finished training. The combined response shapes parameter updates, which change the network’s membrane states and spike behavior. Later calibration then uses this new flip feedback to adjust the dynamic response ranges. In other words, this “averaging” repeats over many training rounds, and earlier “averaging” influences what gets averaged later. This ongoing interaction changes the entire learning process. The final accuracy therefore need not fall between the accuracies obtained using either response alone.
Response to Reviewer 4y1W (part 1/4)
We appreciate reviewer 4y1W’s thoughtful comments and helpful suggestions for strengthening the presentation and evaluation of our work.
Weakness 1: W1. It remains unclear why better alignment between surrogate gradients and hard-spike forward dynamics would necessarily improve the adversarial robustness of SNNs. Intuitively, if the surrogate gradients more accurately reflect spike flips during forward propagation, attackers could also exploit these more informative gradients to generate stronger adversarial examples. This concern is also supported by the findings of [1], which demonstrate that improved surrogate-gradient approximations can lead to more effective adversarial attacks.
Response to Weakness 1:
Thanks for raising this important question.
1. Why better alignment can help robust learning
The key is that surrogate gradients determine which membrane-state changes receive attention during training. For example, a state may contribute little under a clean input, yet undergo a spike flip under a small perturbation that changes the final decision. If the fixed surrogate assigns a weak response to that state, backpropagation can underestimate its importance. The network can then fit clean samples well while giving these vulnerable states too little attention.
Fare uses actual flips and their decision relevance to redirect some backward sensitivity toward these overlooked states, while retaining the original response to support basic learning. This gives parameter updates more useful information about where perturbations affect decisions. Better alignment therefore provides a mechanism for improving learning, while the resulting robustness is checked experimentally. The allocation changes in Figure 6, the feedback-source ablation in Figure 9 (Newly added in the revised manuscript), and the strong-attack results jointly support this explanation.
2. We also give attackers access to Fare’s gradients
We considered this possibility when designing our evaluation, which is why we included “White-box robustness under alternative surrogate-gradient access” in Section 5.1 (p. 7). For each fixed trained model, attackers use Triangle, Sigmoid, Rectangle, and their Fare-adjusted versions to generate adversarial examples. In simple terms, attackers can use the same flip-aware gradients that Fare provides, alongside alternative backward rules.
This directly tests whether changing the attack gradient reveals many previously missed adversarial examples. Across the FGSM and PGD-10 settings in Figure 5, the maximum accuracy reductions are 2.80% and 2.30%, respectively. For example, the CIFAR-10 Fare-Triangle model’s PGD accuracy changes from 33.89% under its native rule to a minimum of 31.82%. There is no abrupt collapse across these tested backward rules, indicating that the model’s performance does not depend on the attacker choosing a particularly ineffective gradient.
3. Stronger attacks provide a further check
The finding in [1] that better gradients can produce stronger attacks is consistent with our reasoning. At attack time, better gradients help expose weaknesses in an already fixed model. During training, Fare uses improved sensitivity information to change the model that is learned. These two effects can coexist.
We further evaluate the final models using longer multi-restart PGD, APGD-CE/DLR, and per-example aggregation across attack losses and backward rules. These additions are highlighted in Section 5.3, “Gradient Obfuscation Checking” (pp. 9–10), with results in Table 3. APGD does uncover weaknesses missed by PGD-10, so we report the aggregated results to reflect this stronger evaluation. Increasing the white-box search from W100 to W200 reduces accuracy by a further 0.09-0.50%. Adding SPSA and Square with 10000 queries causes at most another 0.50% reduction.
Together, these results support that Fare’s robustness under the tested attacks does not come from preventing attackers from effectively using its backward gradients.
For convenience, we reproduce the added discussion (Section 5.3) in the next part of our response.