Related papers: Geometry-Aware Generation of Adversarial Point Clo…
Distributed learning frameworks, which partition neural network models across multiple computing nodes, enhance efficiency in collaborative edge-cloud systems, but may also introduce new vulnerabilities to evasion attacks, often in the form…
Standard approaches for adversarial patch generation lead to noisy conspicuous patterns, which are easily recognizable by humans. Recent research has proposed several approaches to generate naturalistic patches using generative adversarial…
Neural network-based visuomotor policies enable robots to perform manipulation tasks but remain susceptible to perceptual attacks. For example, conventional 2D adversarial patches are effective under fixed-camera setups, where appearance is…
Nowadays more and more data are gathered for detecting and preventing cyber attacks. In cyber security applications, data analytics techniques have to deal with active adversaries that try to deceive the data analytics models and avoid…
Modern applications of artificial neural networks have yielded remarkable performance gains in a wide range of tasks. However, recent studies have discovered that such modelling strategy is vulnerable to Adversarial Examples, i.e. examples…
Autonomous vehicles are typical complex intelligent systems with artificial intelligence at their core. However, perception methods based on deep learning are extremely vulnerable to adversarial samples, resulting in security accidents. How…
The performance of facial super-resolution methods relies on their ability to recover facial structures and salient features effectively. Even though the convolutional neural network and generative adversarial network-based methods deliver…
Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have…
Deep neural networks have been proved that they are vulnerable to adversarial examples, which are generated by adding human-imperceptible perturbations to images. To defend these adversarial examples, various detection based methods have…
The state-of-the-art performance of deep learning algorithms has led to a considerable increase in the utilization of machine learning in security-sensitive and critical applications. However, it has recently been shown that a small and…
Point clouds data, as one kind of representation of 3D objects, are the most primitive output obtained by 3D sensors. Unlike 2D images, point clouds are disordered and unstructured. Hence it is not straightforward to apply classification…
Many recent few-shot learning methods concentrate on designing novel model architectures. In this paper, we instead show that with a simple backbone convolutional network we can even surpass state-of-the-art classification accuracy. The…
Three-dimensional geometric data offer an excellent domain for studying representation learning and generative modeling. In this paper, we look at geometric data represented as point clouds. We introduce a deep AutoEncoder (AE) network with…
3D deep learning models are shown to be as vulnerable to adversarial examples as 2D models. However, existing attack methods are still far from stealthy and suffer from severe performance degradation in the physical world. Although 3D data…
A generative model for high-fidelity point clouds is of great importance in synthesizing 3d environments for applications such as autonomous driving and robotics. Despite the recent success of deep generative models for 2d images, it is…
In the past several decades, many attempts have been made to model synthetic realistic geometric data. The goal of such models is to generate plausible 3D geometries and textures. Perhaps the best known of its kind is the linear 3D…
Vision-based perception modules are increasingly deployed in many applications, especially autonomous vehicles and intelligent robots. These modules are being used to acquire information about the surroundings and identify obstacles. Hence,…
Point cloud completion seeks to recover geometrically consistent shapes from partial or sparse 3D observations. Although recent methods have achieved reasonable global shape reconstruction, they often rely on Euclidean proximity and…
Deep learning models for point clouds have shown to be vulnerable to adversarial attacks, which have received increasing attention in various safety-critical applications such as autonomous driving, robotics, and surveillance. Existing 3D…
Adversarial training and adversarial purification are two widely used defense strategies for enhancing model robustness against adversarial attacks. However, adversarial training requires costly retraining, while adversarial purification…