Spiking Neural Networks (SNNs) offer a promising direction for energy-efficient and brain-inspired computing, yet their vulnerability to adversarial perturbations remains poorly understood. In this work, we revisit the adversarial robustness of SNNs through the lens of temporal ensembling, treating the network as a collection of evolving sub-networks across discrete timesteps. This formulation uncovers two critical but underexplored challenges—the fragility of individual temporal sub-networks and the tendency for adversarial vulnerabilities to transfer across time. To overcome these limitations, we propose Robust Temporal self-Ensemble (RTE), a training framework that improves the robustness of each sub-network while reducing the temporal transferability of adversarial perturbations. RTE integrates both objectives into a unified loss and employs a stochastic sampling strategy for efficient optimization. Extensive experiments across multiple benchmarks demonstrate that RTE consistently outperforms existing training methods in robust-accuracy trade-off. Additional analyses reveal that RTE reshapes the internal robustness landscape of SNNs, leading to more resilient and temporally diversified decision boundaries. Our study highlights the importance of temporal structure in adversarial learning and offers a principled foundation for building robust spiking models.

Decoding non-invasive brain recordings is pivotal for advancing our understanding of human cognition but faces challenges due to individual differences and complex neural signal representations. Traditional methods often require customized models and extensive trials, lacking interpretability in visual reconstruction tasks. Our framework integrates 3D brain structures with visual semantics using a *Vision Transformer 3D*. This unified feature extractor efficiently aligns fMRI features with multiple levels of visual embeddings, eliminating the need for subject-specific models and allowing extraction from single-trial data. The extractor consolidates multi-level visual features into one network, simplifying integration with Large Language Models (LLMs). Additionally, we have enhanced the fMRI dataset with diverse fMRI-image-related textual data to support multimodal large model development. Integrating with LLMs enhances decoding capabilities, enabling tasks such as brain captioning, complex reasoning, concept localization, and visual reconstruction. Our approach demonstrates superior performance across these tasks, precisely identifying language-based concepts within brain signals, enhancing interpretability, and providing deeper insights into neural processes. These advances significantly broaden the applicability of non-invasive brain decoding in neuroscience and human-computer interaction, setting the stage for advanced brain-computer interfaces and cognitive models.

Spiking neural network (SNN) has attracted much attention due to its powerful spatio-temporal information representation ability. Capsule Neural Network (CapsNet) does well in assembling and coupling features of different network layers. Here, we propose Spiking CapsNet by combining spiking neurons and capsule structures. In addition, we propose a more biologically plausible Spike Timing Dependent Plasticity routing mechanism. The coupling ability is further improved by fully considering the spatio-temporal relationship between spiking capsules of the low layer and the high layer. We have verified experiments on the MNIST, FashionMNIST, and CIFAR10 datasets. Our algorithm still shows comparable performance concerning other excellent SNNs with typical structures (convolutional, fully-connected) on these classification tasks. Our Spiking CapsNet combines SNN and CapsNet’s strengths and shows strong robustness to noise and affine transformation. By adding different Salt-Pepper and Gaussian noise to the test dataset, the experimental results demonstrate that our algorithm is more resistant to noise than other approaches. As well, our Spiking CapsNet shows strong generalization to affine transformation on the AffNIST dataset. Our code is available at https://github.com/BrainCog-X/Brain-Cog.

This paper addresses the problem of freehand ultrasound probe tracking without requiring an external tracking device, by mounting a video camera on the probe to identify location relative to the patient's external anatomy. By pre-acquiring a high-resolution 3D surface map as an atlas of the anatomy, we eliminate the need for artificial skin markers. We use an OpenDR pipeline for inverse rendering and pose estimation via matching the real-time camera image with the 3D surface map. We have addressed the problem of distinguishing rotation from translation by including an inertial navigation system to accurately measure rotation. Experiments on both a phantom containing an image of human skin (palm) as well as actual human skin (fingers, palm, and wrist) validate the effectiveness of our approach. For ultrasound, this will permit the compilation of 3D ultrasound data as the probe is moved, as well as comparison of real-time ultrasound scans registered with previous scans from the same anatomical location. In a broader sense, tools that know where they are by looking at the patient's exterior could have broad beneficial impact on clinical medicine.