Keke Tang
YOU?
Author Swipe
View article: Transferable and Undefendable Point Cloud Attacks via Medial Axis Transform
Transferable and Undefendable Point Cloud Attacks via Medial Axis Transform Open
Studying adversarial attacks on point clouds is essential for evaluating and improving the robustness of 3D deep learning models. However, most existing attack methods are developed under ideal white-box settings and often suffer from limi…
View article: SEER: Semantic Enhancement and Emotional Reasoning Network for Multimodal Fake News Detection
SEER: Semantic Enhancement and Emotional Reasoning Network for Multimodal Fake News Detection Open
Previous studies on multimodal fake news detection mainly focus on the alignment and integration of cross-modal features, as well as the application of text-image consistency. However, they overlook the semantic enhancement effects of larg…
View article: AdvGrasp: Adversarial Attacks on Robotic Grasping from a Physical Perspective
AdvGrasp: Adversarial Attacks on Robotic Grasping from a Physical Perspective Open
Adversarial attacks on robotic grasping provide valuable insights into evaluating and improving the robustness of these systems. Unlike studies that focus solely on neural network predictions while overlooking the physical principles of gr…
View article: SourceDetMamba: A Graph-aware State Space Model for Source Detection in Sequential Hypergraphs
SourceDetMamba: A Graph-aware State Space Model for Source Detection in Sequential Hypergraphs Open
Source detection on graphs has demonstrated high efficacy in identifying rumor origins. Despite advances in machine learning-based methods, many fail to capture intrinsic dynamics of rumor propagation. In this work, we present SourceDetMam…
View article: HyperDet: Source Detection in Hypergraphs via Interactive Relationship Construction and Feature-rich Attention Fusion
HyperDet: Source Detection in Hypergraphs via Interactive Relationship Construction and Feature-rich Attention Fusion Open
Hypergraphs offer superior modeling capabilities for social networks, particularly in capturing group phenomena that extend beyond pairwise interactions in rumor propagation. Existing approaches in rumor source detection predominantly focu…
View article: PLGNN: graph neural networks via adaptive feature perturbation and high-way links
PLGNN: graph neural networks via adaptive feature perturbation and high-way links Open
Graph neural networks (GNNs) have exhibited remarkable performance in addressing diverse graph learning tasks. However, inevitable missing information in graph networks hinders GNNs from aggregating more abundant feature information, limit…
View article: Hypergraph Attacks via Injecting Homogeneous Nodes into Elite Hyperedges
Hypergraph Attacks via Injecting Homogeneous Nodes into Elite Hyperedges Open
Recent studies have shown that Hypergraph Neural Networks (HGNNs) are vulnerable to adversarial attacks. Existing approaches focus on hypergraph modification attacks guided by gradients, overlooking node spanning in the hypergraph and the …
View article: Imperceptible 3D Point Cloud Attacks on Lattice-based Barycentric Coordinates
Imperceptible 3D Point Cloud Attacks on Lattice-based Barycentric Coordinates Open
Imperceptible adversarial attacks on 3D point clouds rely on effective constraints. While manifold constraints have notable advantages over Euclidean ones, the global parameterization used in current methods often fails to fully preserve m…
View article: EOOD: Entropy-based Out-of-distribution Detection
EOOD: Entropy-based Out-of-distribution Detection Open
Deep neural networks (DNNs) often exhibit overconfidence when encountering out-of-distribution (OOD) samples, posing significant challenges for deployment. Since DNNs are trained on in-distribution (ID) datasets, the information flow of ID…
View article: Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field
Imperceptible Adversarial Attacks on Point Clouds Guided by Point-to-Surface Field Open
Adversarial attacks on point clouds are crucial for assessing and improving the adversarial robustness of 3D deep learning models. Traditional solutions strictly limit point displacement during attacks, making it challenging to balance imp…
View article: Hypergraph Attacks via Injecting Homogeneous Nodes into Elite Hyperedges
Hypergraph Attacks via Injecting Homogeneous Nodes into Elite Hyperedges Open
Recent studies have shown that Hypergraph Neural Networks (HGNNs) are vulnerable to adversarial attacks. Existing approaches focus on hypergraph modification attacks guided by gradients, overlooking node spanning in the hypergraph and the …
View article: fairGNN-WOD: Fair Graph Learning Without Complete Demographics
fairGNN-WOD: Fair Graph Learning Without Complete Demographics Open
Graph Neural Networks (GNNs) have excelled in diverse applications due to their outstanding predictive performance, yet they often overlook fairness considerations, prompting numerous recent efforts to address this societal concern. Howeve…
View article: Node Injection Attack Based on Label Propagation Against Graph Neural Network
Node Injection Attack Based on Label Propagation Against Graph Neural Network Open
Graph Neural Network (GNN) has achieved remarkable success in various graph\nlearning tasks, such as node classification, link prediction and graph\nclassification. The key to the success of GNN lies in its effective structure\ninformation…
View article: Multimodal fake news detection through intra-modality feature aggregation and inter-modality semantic fusion
Multimodal fake news detection through intra-modality feature aggregation and inter-modality semantic fusion Open
The prevalence of online misinformation, termed “fake news”, has exponentially escalated in recent years. These deceptive information, often rich with multimodal content, can easily deceive individuals into spreading them via various socia…
View article: A Comprehensive Survey on Evaluating Large Language Model Applications in the Medical Industry
A Comprehensive Survey on Evaluating Large Language Model Applications in the Medical Industry Open
Since the inception of the Transformer architecture in 2017, Large Language Models (LLMs) such as GPT and BERT have evolved significantly, impacting various industries with their advanced capabilities in language understanding and generati…
View article: A General Black-box Adversarial Attack on Graph-based Fake News Detectors
A General Black-box Adversarial Attack on Graph-based Fake News Detectors Open
Graph Neural Network (GNN)-based fake news detectors apply various methods to construct graphs, aiming to learn distinctive news embeddings for classification. Since the construction details are unknown for attackers in a black-box scenari…
View article: GIN-SD: Source Detection in Graphs with Incomplete Nodes via Positional Encoding and Attentive Fusion
GIN-SD: Source Detection in Graphs with Incomplete Nodes via Positional Encoding and Attentive Fusion Open
Source detection in graphs has demonstrated robust efficacy in the domain of rumor source identification. Although recent solutions have enhanced performance by leveraging deep neural networks, they often require complete user data. In thi…
View article: Manifold Constraints for Imperceptible Adversarial Attacks on Point Clouds
Manifold Constraints for Imperceptible Adversarial Attacks on Point Clouds Open
Adversarial attacks on 3D point clouds often exhibit unsatisfactory imperceptibility, which primarily stems from the disregard for manifold-aware distortion, i.e., distortion of the underlying 2-manifold surfaces. In this paper, we develop…
View article: Cross-Domain Contrastive Learning-Based Few-Shot Underwater Acoustic Target Recognition
Cross-Domain Contrastive Learning-Based Few-Shot Underwater Acoustic Target Recognition Open
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 datase…
View article: Deep Manifold Attack on Point Clouds via Parameter Plane Stretching
Deep Manifold Attack on Point Clouds via Parameter Plane Stretching Open
Adversarial attack on point clouds plays a vital role in evaluating and improving the adversarial robustness of 3D deep learning models. Current attack methods are mainly applied by point perturbation in a non-manifold manner. In this pape…
View article: SGMA: a novel adversarial attack approach with improved transferability
SGMA: a novel adversarial attack approach with improved transferability Open
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 ge…
View article: AdvSCOD: Bayesian-Based Out-Of-Distribution Detection via Curvature Sketching and Adversarial Sample Enrichment
AdvSCOD: Bayesian-Based Out-Of-Distribution Detection via Curvature Sketching and Adversarial Sample Enrichment Open
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 usin…
View article: Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding
Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding Open
This paper addresses the task of temporal sentence grounding (TSG). Although many respectable works have made decent achievements in this important topic, they severely rely on massive expensive video-query paired annotations, which requir…
View article: Spatio-Frequency Decoupled Weak-Supervision for Face Reconstruction
Spatio-Frequency Decoupled Weak-Supervision for Face Reconstruction Open
3D face reconstruction has witnessed considerable progress in recovering 3D face shapes and textures from in-the-wild images. However, due to a lack of texture detail information, the reconstructed shape and texture based on deep learning …
View article: NormalAttack: Curvature-Aware Shape Deformation along Normals for Imperceptible Point Cloud Attack
NormalAttack: Curvature-Aware Shape Deformation along Normals for Imperceptible Point Cloud Attack Open
Many efforts have been made on developing adversarial attack methods on point clouds. However, without fully considering the geometric property of point clouds, existing methods tend to produce clearly visible outliers. In this paper, we p…
View article: HOME: 3D Human–Object Mesh Topology-Enhanced Interaction Recognition in Images
HOME: 3D Human–Object Mesh Topology-Enhanced Interaction Recognition in Images Open
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 …
View article: Adversarial Attacks on ASR Systems: An Overview
Adversarial Attacks on ASR Systems: An Overview Open
With the development of hardware and algorithms, ASR(Automatic Speech Recognition) systems evolve a lot. As The models get simpler, the difficulty of development and deployment become easier, ASR systems are getting closer to our life. On …
View article: Multi-task super resolution method for vector field critical points enhancement
Multi-task super resolution method for vector field critical points enhancement Open
It is a challenging task to handle the vector field visualization at local critical points. Generally, topological based methods firstly divide critical regions into different categories, and then process the different types of critical re…