Related papers: SAGA: Spectral Adversarial Geometric Attack on 3D …
Deep neural network models are used today in various applications of artificial intelligence, the strengthening of which, in the face of adversarial attacks is of particular importance. An appropriate solution to adversarial attacks is…
Spatially localized deformation components are very useful for shape analysis and synthesis in 3D geometry processing. Several methods have recently been developed, with an aim to extract intuitive and interpretable deformation components.…
We propose a method to reconstruct, complete and semantically label a 3D scene from a single input depth image. We improve the accuracy of the regressed semantic 3D maps by a novel architecture based on adversarial learning. In particular,…
Deep neural networks (DNNs) have become essential for processing the vast amounts of aerial imagery collected using earth-observing satellite platforms. However, DNNs are vulnerable towards adversarial examples, and it is expected that this…
Adversarial perturbations can pose a serious threat for deploying machine learning systems. Recent works have shown existence of image-agnostic perturbations that can fool classifiers over most natural images. Existing methods present…
While DeepFake applications are becoming popular in recent years, their abuses pose a serious privacy threat. Unfortunately, most related detection algorithms to mitigate the abuse issues are inherently vulnerable to adversarial attacks…
3D shape analysis is an important research topic in computer vision and graphics. While existing methods have generalized image-based deep learning to meshes using graph-based convolutions, the lack of an effective pooling operation…
The majority of methods for crafting adversarial attacks have focused on scenes with a single dominant object (e.g., images from ImageNet). On the other hand, natural scenes include multiple dominant objects that are semantically related.…
Generative Adversarial Networks (GANs) have become predominant in image generation tasks. Their success is attributed to the training regime which employs two models: a generator G and discriminator D that compete in a minimax zero sum…
Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. We propose a geometric framework,…
Shadow removal is a task aimed at erasing regional shadows present in images and reinstating visually pleasing natural scenes with consistent illumination. While recent deep learning techniques have demonstrated impressive performance in…
Though deep neural models adopted to realize the perception of autonomous driving have proven vulnerable to adversarial examples, known attacks often leverage 2D patches and target mostly monocular perception. Therefore, the effectiveness…
Deep neural networks are susceptible to \emph{adversarial} attacks. In computer vision, well-crafted perturbations to images can cause neural networks to make mistakes such as confusing a cat with a computer. Previous adversarial attacks…
This paper described a method for reconstruction of detailed-resolution depth structure maps, usually obtained after the 3D seismic surveys, using the data from 2D seismic depth maps. The method uses two algorithms based on the…
Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of…
Similarity measures are widely used to interpret the representational geometries used by neural networks to solve tasks. Yet, because existing methods compare the extrinsic geometry of representations in state space, rather than their…
Deep networks are well-known to be fragile to adversarial attacks. We conduct an empirical analysis of deep representations under the state-of-the-art attack method called PGD, and find that the attack causes the internal representation to…
Metasurfaces have become a promising means for manipulating optical wavefronts in flat and high-performance optical devices. Conventional metasurface device design relies on trial-and-error methods to obtain target electromagnetic (EM)…
It is imperative to ensure the robustness of deep learning models in critical applications such as, healthcare. While recent advances in deep learning have improved the performance of volumetric medical image segmentation models, these…
In recent years, a significant amount of research efforts concentrated on adversarial attacks on images, while adversarial video attacks have seldom been explored. We propose an adversarial attack strategy on videos, called DeepSAVA. Our…