🤖 AI Summary
This work addresses the underexplored vulnerability of event-driven spiking neural network (SNN)–based object detection models to availability-oriented backdoor attacks. We propose the Event Burst Trigger (EBT) attack, which injects carefully crafted event-based triggers into training data to induce dense event streams during inference, thereby significantly increasing the computational overhead of non-maximum suppression (NMS) and degrading system availability. Notably, EBT requires no modifications to the model architecture, loss function, or inference pipeline, allowing it to evade existing detection mechanisms such as STRIP. Experimental results demonstrate that, with less than a 0.099 drop in mAP@0.5, the attack can increase NMS latency by up to 38%, effectively elevating resource consumption and reducing scheduling slack without producing conspicuous resource usage spikes.
📝 Abstract
Event-based vision and spiking neural networks (SNNs) are increasingly adopted for edge intelligence under strict latency and energy constraints. However, the vulnerability of event-based SNN object detection models to availability backdoor attacks remains insufficiently studied. This paper presents Event Burst Trigger (EBT), an availability backdoor attack targeting SNN-based object detection models. EBT injects carefully crafted event-based triggers into the training data, which induce temporally concentrated event streams during inference. These burst-like activations increase the number of phantom (i.e., spurious) object candidates, and consequently inflate the computational cost of the post-processing stage, particularly Non-Maximum Suppression (NMS). We evaluate EBT on SpikeYOLO, the state-of-the-art SNN-based object detector, under a poison-only threat model that does not require modifications to the model architecture, loss function, or inference pipeline. Experimental results show that while detection accuracy remains largely preserved, with mAP@0.5 decreasing by less than 0.099, the latency of the NMS stage increases by up to 38%. This indicates that NMS can become a dominant availability bottleneck in event-based SNN object detection. Experiments on an edge platform further show that the proposed attack elevates baseline resource utilization and reduces scheduling slack without inducing conspicuous peaks in resource usage. In addition, STRIP-based backdoor detection fails to reliably distinguish the proposed attack from benign inputs. These results characterize a previously underexplored availability backdoor threat in event-based SNN object detection systems.