相关论文: DUP-Net: Denoiser and Upsampler Network for 3D Adv…

Deep neural networks (DNNs) are notoriously vulnerable to adversarial attacks that place carefully crafted perturbations on normal examples to fool DNNs. To better understand such attacks, a characterization of the features carried by…

Image compression-based approaches for defending against the adversarial-example attacks, which threaten the safety use of deep neural networks (DNN), have been investigated recently. However, prior works mainly rely on directly tuning…

Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e.g. cartoon. However, in terms of visual perception of Deep Neural Networks (DNNs), the ability for recognizing abstract…

In light of rising cybersecurity threats, data center providers face growing pressure to protect their own management infrastructure from Distributed Denial-of-Service (DDoS) attacks. While tenant-managed cages generally fall outside the…

Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock…

Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be…

Recently MLP-based methods have shown strong performance in point cloud analysis. Simple MLP architectures are able to learn geometric features in local point groups yet fail to model long-range dependencies directly. In this paper, we…

Deep Neural Networks (DNNs) in Computer Vision (CV) are well-known to be vulnerable to Adversarial Examples (AEs), namely imperceptible perturbations added maliciously to cause wrong classification results. Such variability has been a…

Deep neural networks (DNNs) deployed in real-world applications can encounter out-of-distribution (OOD) data and adversarial examples. These represent distinct forms of distributional shifts that can significantly impact DNNs' reliability…

With the increasing amount of available data and advances in computing capabilities, deep neural networks (DNNs) have been successfully employed to solve challenging tasks in various areas, including healthcare, climate, and finance.…

The vulnerabilities of deep neural networks against singularities have raised serious concerns regarding their deployment in the physical world. One of the most prominent and impactful physical-world adversarial perturbations is the…

Selection is a fundamental task in exploratory analysis and visualization of 3D point clouds. Prior researches on selection methods were developed mainly based on heuristics such as local point density, thus limiting their applicability in…

Deep Neural Networks for image classification have been found to be vulnerable to adversarial samples, which consist of sub-perceptual noise added to a benign image that can easily fool trained neural networks, posing a significant risk to…

Established sampling protocols for 3D point cloud learning, such as Farthest Point Sampling (FPS) and Fixed Sample Size (FSS), have long been relied upon. However, real-world data often suffer from corruptions, such as sensor noise, which…

Neural operators have emerged as fast surrogate models for physics simulations, yet they remain acutely vulnerable to adversarial perturbations, a critical liability for safety-critical digital twin deployments. We present a synergistic…

Self-supervised methods have been proven effective for learning deep representations of 3D point cloud data. Although recent methods in this domain often rely on random masking of inputs, the results of this approach can be improved. We…

Point cloud based place recognition is still an open issue due to the difficulty in extracting local features from the raw 3D point cloud and generating the global descriptor, and it's even harder in the large-scale dynamic environments. In…

Point cloud classifiers with rotation robustness have been widely discussed in the 3D deep learning community. Most proposed methods either use rotation invariant descriptors as inputs or try to design rotation equivariant networks.…

3D computer vision models are commonly used in security-critical applications such as autonomous driving and surgical robotics. Emerging concerns over the robustness of these models against real-world deformations must be addressed…

Deep neural networks (DNNs) provide excellent performance across a wide range of classification tasks, but their training requires high computational resources and is often outsourced to third parties. Recent work has shown that outsourced…