Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916908569198592 |
|---|---|
| author | Kang, Donghwa Kim, Doohyun Ko, Sang-Ki Lee, Jinkyu Baek, Hyeongboo Kang, Brent ByungHoon |
| author_facet | Kang, Donghwa Kim, Doohyun Ko, Sang-Ki Lee, Jinkyu Baek, Hyeongboo Kang, Brent ByungHoon |
| contents | State-of-the-art (SOTA) gradient-based adversarial attacks on spiking neural networks (SNNs), which largely rely on extending FGSM and PGD frameworks, face a critical limitation: substantial attack latency from multi-timestep processing, rendering them infeasible for practical real-time applications. This inefficiency stems from their design as direct extensions of ANN paradigms, which fail to exploit key SNN properties. In this paper, we propose the timestep-compressed attack (TCA), a novel framework that significantly reduces attack latency. TCA introduces two components founded on key insights into SNN behavior. First, timestep-level backpropagation (TLBP) is based on our finding that global temporal information in backpropagation to generate perturbations is not critical for an attack's success, enabling per-timestep evaluation for early stopping. Second, adversarial membrane potential reuse (A-MPR) is motivated by the observation that initial timesteps are inefficiently spent accumulating membrane potential, a warm-up phase that can be pre-calculated and reused. Our experiments on VGG-11 and ResNet-17 with the CIFAR-10/100 and CIFAR10-DVS datasets show that TCA significantly reduces the required attack latency by up to 56.6% and 57.1% compared to SOTA methods in white-box and black-box settings, respectively, while maintaining a comparable attack success rate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_13812 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation Kang, Donghwa Kim, Doohyun Ko, Sang-Ki Lee, Jinkyu Baek, Hyeongboo Kang, Brent ByungHoon Computer Vision and Pattern Recognition Neural and Evolutionary Computing State-of-the-art (SOTA) gradient-based adversarial attacks on spiking neural networks (SNNs), which largely rely on extending FGSM and PGD frameworks, face a critical limitation: substantial attack latency from multi-timestep processing, rendering them infeasible for practical real-time applications. This inefficiency stems from their design as direct extensions of ANN paradigms, which fail to exploit key SNN properties. In this paper, we propose the timestep-compressed attack (TCA), a novel framework that significantly reduces attack latency. TCA introduces two components founded on key insights into SNN behavior. First, timestep-level backpropagation (TLBP) is based on our finding that global temporal information in backpropagation to generate perturbations is not critical for an attack's success, enabling per-timestep evaluation for early stopping. Second, adversarial membrane potential reuse (A-MPR) is motivated by the observation that initial timesteps are inefficiently spent accumulating membrane potential, a warm-up phase that can be pre-calculated and reused. Our experiments on VGG-11 and ResNet-17 with the CIFAR-10/100 and CIFAR10-DVS datasets show that TCA significantly reduces the required attack latency by up to 56.6% and 57.1% compared to SOTA methods in white-box and black-box settings, respectively, while maintaining a comparable attack success rate. |
| title | Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation |
| topic | Computer Vision and Pattern Recognition Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2508.13812 |