AI summaryⓘ
The authors studied a special type of cyberattack called Event Burst Trigger (EBT) on object detection systems that use event-based vision and spiking neural networks (SNNs). This attack inserts fake bursts of events into training data, causing the system to generate many false object detections during use, which slows down a key processing step called Non-Maximum Suppression (NMS). Their tests showed that while the detection accuracy stayed nearly the same, the slowdowns could reach 38%, making the system less usable. The attack also evaded standard detection methods and increased resource use subtly on edge devices. This work highlights a new kind of threat affecting the availability of event-based SNN object detection systems.
event-based visionspiking neural networksobject detectionbackdoor attackEvent Burst TriggerNon-Maximum Suppressionpoison-only attackedge computingSTRIP detectionlatency
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.