Deep learning models are easily deceived by adversarial examples, and transferable attacks are crucial because of the inaccessibility of model information. Existing SOTA attack approaches tend to ...destroy important features of objects to generate adversarial examples. This paper proposes the split grid mask attack (SGMA), which reduces the intensity of model-specific features by split grid mask transformation, effectively highlighting the important features of the input image. Perturbing these important features can guide the development of adversarial examples in a more transferable direction. Specifically, we introduce the split grid mask transformation into the input image. Due to the vulnerability of model-specific features to image transformations, the intensity of model-specific features decreases after aggregation while the intensities of important features remain. The generated adversarial examples guided by destroying important features have excellent transferability. Extensive experimental results demonstrate the effectiveness of the proposed SGMA. Compared to the SOTA attack approaches, our method improves the black-box attack success rates by an average of 6.4% and 8.2% against the normally trained models and the defense ones respectively.
The number of patients with Alzheimer's disease (AD) worldwide is increasing yearly, but the existing treatment methods have poor efficacy. Transcranial alternating current stimulation (tACS) is a ...new treatment for AD, but the offline effect of tACS is insufficient. To prolong the offline effect, we designed to combine tACS with sound stimulation to maintain the long-term post-effect.
To explore the safety and effectiveness of tACS combined with sound stimulation and its impact on the cognition of AD patients. This trial will recruit 87 patients with mild to moderate AD. All patients were randomly divided into three groups. The change in Alzheimer's Disease Assessment Scale-Cognitive (ADAS-Cog) scores from the day before treatment to the end of treatment and 3 months after treatment was used as the main evaluation index. We will also explore the changes in the brain structural network, functional network, and metabolic network of AD patients in each group after treatment.
We hope to conclude that tACS combined with sound stimulation is safe and tolerable in 87 patients with mild to moderate AD under three standardized treatment regimens. Compared with tACS alone or sound alone, the combination group had a significant long-term effect on cognitive improvement. To screen out a better treatment plan for AD patients. tACS combined with sound stimulation is a previously unexplored, non-invasive joint intervention to improve patients' cognitive status. This study may also identify the potential mechanism of tACS combined with sound stimulation in treating mild to moderate AD patients.
Clinicaltrials.gov, NCT05251649. Registered on February 22, 2022.
Transcranial alternating current stimulation (tACS) is a relatively new non-invasive brain electrical stimulation method for the treatment of patients with Alzheimer's disease (AD), but it has poor ...offline effects. Therefore, we applied a new combined stimulation method to observe the offline effect on the cognitive function of patients with AD. Here, we describe the clinical results of a case in which tACS combined with sound stimulation was applied to treat moderate AD. The patient was a 73-year-old woman with a 2-year history of persistent cognitive deterioration despite the administration of Aricept and Sodium Oligomannate. Therefore, the patient received tACS combined with sound stimulation. Her cognitive scale scores improved after 15 sessions and continued to improve at 4 months of follow-up. Although the current report may provide a new alternative therapy for patients with AD, more clinical data are needed to support its efficacy.
Trial registration
Clinicaltrials.gov
, NCT05251649.
Dysbiosis of the gut microbiota is pivotal in Crohn's disease (CD) and modulated by host physiological conditions. Hyperbaric oxygen therapy (HBOT) is a promising treatment for CD that can regulate ...gut microbiota. The relationship between HBOT and the gut microbiota in CD remains unknown.
CD patients were divided into an HBOT group (n = 10) and a control group (n = 10) in this open-label prospective interventional study. The fecal samples before and after HBOT were used for 16 S rRNA gene sequencing and fecal microbiota transplantation (FMT). A colitis mouse model was constructed using dextran sulfate sodium, and intestinal and systematic inflammation was evaluated. The safety and long-term effect of HBOT were observed.
HBOT significantly reduced the level of C-reactive protein (CRP) (80.79 ± 42.05 mg/L vs. 33.32 ± 18.31 mg/L, P = 0.004) and the Crohn's Disease Activity Index (CDAI) (274.87 ± 65.54 vs. 221.54 ± 41.89, P = 0.044). HBOT elevated the declined microbial diversity and ameliorated the altered composition of gut microbiota in patients with CD. The relative abundance of Escherichia decreased, and that of Bifidobacterium and Clostridium XIVa increased after HBOT. Mice receiving FMT from donors after HBOT had significantly less intestinal inflammation and serum CRP than the group before HBOT. HBOT was safe and well-tolerated by patients with CD. Combined with ustekinumab, more patients treated with HBOT achieved clinical response (30%vs.70%, P = 0.089) and remission (20%vs.50%, P = 0.160) at week 4.
HBOT modulates the dysbiosis of gut microbiota in CD and ameliorates intestinal and systematic inflammation. HBOT is a safe option for CD and exhibits a promising auxiliary effect to ustekinumab.
Chinese Clinical Trial Registry, ChiCTR2200061193. Registered 15 June 2022, https://www.chictr.org.cn/showproj.html?proj=171605 .
Detecting out-of-distribution (OOD) samples is critical for the deployment of deep neural networks (DNN) in real-world scenarios. An appealing direction in which to conduct OOD detection is to ...measure the epistemic uncertainty in DNNs using the Bayesian model, since it is much more explainable. SCOD sketches the curvature of DNN classifiers based on Bayesian posterior estimation and decomposes the OOD measurement into the uncertainty of the model parameters and the influence of input samples on the DNN models. However, since lots of approximation is applied, and the influence of the input samples on DNN models can be hardly measured stably, as demonstrated in adversarial attacks, the detection is not robust. In this paper, we propose a novel AdvSCOD framework that enriches the input sample with a small set of its neighborhoods generated by applying adversarial perturbation, which we believe can better reflect the influence on model predictions, and then we average their uncertainties, measured by SCOD. Extensive experiments with different settings of in-distribution and OOD datasets validate the effectiveness of AdvSCOD in OOD detection and its superiority to state-of-the-art Bayesian-based methods. We also evaluate the influence of different types of perturbation.
Recognizing 3-D objects in cluttered scenes is a challenging task. Common approaches find potential feature correspondences between a scene and candidate models by matching sampled local shape ...descriptors and select a few correspondences with the highest descriptor similarity to identify models that appear in the scene. However, real scans contain various nuisances, such as noise, occlusion, and featureless object regions. This makes selected correspondences have a certain portion of false positives, requiring adopting the time-consuming model verification many times to ensure accurate recognition. This paper proposes a 3-D object recognition approach with three key components. First, we construct a Signature of Geometric Centroids descriptor that is descriptive and robust, and apply it to find high-quality potential feature correspondences. Second, we measure geometric compatibility between a pair of potential correspondences based on isometry and three angle-preserving components. Third, we perform effective correspondence selection by using both descriptor similarity and compatibility with an auxiliary set of "less" potential correspondences. Experiments on publicly available data sets demonstrate the robustness and/or efficiency of the descriptor, selection approach, and recognition framework. Comparisons with the state-of-the-arts validate the superiority of our recognition approach, especially under challenging scenarios.
Dissection puzzles require assembling a common set of pieces into multiple distinct forms. Existing works focus on creating 2D dissection puzzles that form primitive or naturalistic shapes. Unlike 2D ...dissection puzzles that could be supported on a tabletop surface, 3D dissection puzzles are preferable to be steady by themselves for each assembly form. In this work, we aim at computationally designing steady 3D dissection puzzles. We address this challenging problem with three key contributions. First, we take two voxelized shapes as inputs and dissect them into a common set of puzzle pieces, during which we allow slightly modifying the input shapes, preferably on their internal volume, to preserve the external appearance. Second, we formulate a formal model of generalized interlocking for connecting pieces into a steady assembly using both their geometric arrangements and friction. Third, we modify the geometry of each dissected puzzle piece based on the formal model such that each assembly form is steady accordingly. We demonstrate the effectiveness of our approach on a wide variety of shapes, compare it with the state‐of‐the‐art on 2D and 3D examples, and fabricate some of our designed puzzles to validate their steadiness.
Microcracks in concrete can coalesce into larger cracks that further propagate under repetitive load cycles. Complex process of crack formation and growth are essentially involved in the failure ...mechanism of concrete. Understanding the crack formation and propagation is one of the core issues in fatigue damage evaluation of concrete materials and components. In this regard, a numerical model was formulated to simulate the thorough failure process, ranging from microcracks growth, crack coalescence, macrocrack formation and propagation, to the final rupture. This model is applied to simulate the fatigue rupture of three-point bending concrete beams at different stress levels. Numerical results are qualitatively consistent with the experimental observations published in literature. Furthermore, in the framework of damage mechanics, one damage variable is defined to reflect stiffness reduction caused by fatigue loading. S-N curve is subsequently computed and the macroscopic damage evolution of concrete beams are achieved. By employing the combined approaches of fracture mechanics and damage mechanics, made possible is the damage evolution of concrete beam as well as the microscopic multiple fatigue crack simulation. The proposed approach has the potential to be applied to the fatigue life assessment of materials and components at various scales in engineering practice.
Underwater Acoustic Target Recognition (UATR) plays a crucial role in underwater detection devices. However, due to the difficulty and high cost of collecting data in the underwater environment, UATR ...still faces the problem of small datasets. Few-shot learning (FSL) addresses this challenge through techniques such as Siamese networks and prototypical networks. However, it also suffers from the issue of overfitting, which leads to catastrophic forgetting and performance degradation. Current underwater FSL methods primarily focus on mining similar information within sample pairs, ignoring the unique features of ship radiation noise. This study proposes a novel cross-domain contrastive learning-based few-shot (CDCF) method for UATR to alleviate overfitting issues. This approach leverages self-supervised training on both source and target domains to facilitate rapid adaptation to the target domain. Additionally, a base contrastive module is introduced. Positive and negative sample pairs are generated through data augmentation, and the similarity in the corresponding frequency bands of feature embedding is utilized to learn fine-grained features of ship radiation noise, thereby expanding the scope of knowledge in the source domain. We evaluate the performance of CDCF in diverse scenarios on ShipsEar and DeepShip datasets. The experimental results indicate that in cross-domain environments, the model achieves accuracy rates of 56.71%, 73.02%, and 76.93% for 1-shot, 3-shot, and 5-shot scenarios, respectively, outperforming other FSL methods. Moreover, the model demonstrates outstanding performance in noisy environments.
Human–object interaction (HOI) recognition is a very challenging task due to the ambiguity brought by occlusions, viewpoints, and poses. Because of the limited interaction information in the image ...domain, extracting 3D features of a point cloud has been an important means to improve the recognition performance of HOI. However, the features neglect topological features of adjacent points at low level, and the deep topology relation between a human and an object at high level. In this paper, we present a 3D human–object mesh topology enhanced method (HOME) for HOI recognition in images. In the method, human–object mesh (HOM) is built by integrating the reconstructed human and object mesh from images firstly. Therefore, under the assumption that the interaction comes from the macroscopic pattern constructed by spatial position and microscopic topology of human–object, HOM is inputted into MeshCNN to extract the effective edge features by edge-based convolution from bottom to up, as the topological features that encode the invariance of the interaction relationship. At last, topological cues are fused with visual cues to enhance the recognition performance greatly. In the experiment, HOI recognition results have achieved an improvement of about 4.3% mean average precision (mAP) in the Rare cases of the HICO-DET dataset, which verifies the effectiveness of the proposed method.