Search Results for author:
Found 23 papers, 5 papers with code
Theoretical Understanding of Learning from Adversarial Perturbations
In this study, we provide a theoretical framework for understanding learning from perturbations using a one-hidden-layer network trained on mutually orthogonal samples.
Identifying Important Group of Pixels using Interactions
To better understand the behavior of image classifiers, it is useful to visualize the contribution of individual pixels to the model prediction.
Learning to Compute Gröbner Bases
Solving a polynomial system, or computing an associated Gr\"obner basis, has been a fundamental task in computational algebra.
Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognition
Using Fourier analysis, we explore the robustness and vulnerability of graph convolutional neural networks (GCNs) for skeleton-based action recognition.
Exploiting Frequency Spectrum of Adversarial Images for General Robustness
In recent years, there has been growing concern over the vulnerability of convolutional neural networks (CNNs) to image perturbations.
Improving Zero-Shot Action Recognition using Human Instruction with Text Description
Furthermore, the proposed model can also be combined with other models to improve its accuracy.
Vanishing Component Analysis with Contrastive Normalization
Vanishing component analysis (VCA) computes approximate generators of vanishing ideals of samples, which are further used for extracting nonlinear features of the samples.
Game-Theoretic Understanding of Misclassification
This paper analyzes various types of image misclassification from a game-theoretic view.
Approximate Vanishing Ideal Computations at Scale
The vanishing ideal of a set of points $X = \{\mathbf{x}_1, \ldots, \mathbf{x}_m\}\subseteq \mathbb{R}^n$ is the set of polynomials that evaluate to $0$ over all points $\mathbf{x} \in X$ and admits an efficient representation by a finite subset of generators.
Superclass Adversarial Attack
Adversarial attacks have only focused on changing the predictions of the classifier, but their danger greatly depends on how the class is mistaken.
Adversarial joint attacks on legged robots
In experiments with the quadruped robot Ant-v2 and the bipedal robot Humanoid-v2, in OpenAI Gym environments, we find that differential evolution can efficiently find the strongest torque perturbations among the three methods.
Adversarial Body Shape Search for Legged Robots
We propose an evolutionary computation method for an adversarial attack on the length and thickness of parts of legged robots by deep reinforcement learning.
Adversarial amplitude swap towards robust image classifiers
Extensive experiments revealed that the images generated by combining the amplitude spectrum of adversarial images and the phase spectrum of clean images accommodates moderate and general perturbations, and training with these images equips a CNN classifier with more general robustness, performing well under both common corruptions and adversarial perturbations.
Reinforcement Learning with Adaptive Curriculum Dynamics Randomization for Fault-Tolerant Robot Control
This study is aimed at addressing the problem of fault tolerance of quadruped robots to actuator failure, which is critical for robots operating in remote or extreme environments.
Adversarially Trained Object Detector for Unsupervised Domain Adaptation
In addition, we propose a method that combines adversarial training and feature alignment to ensure the improved alignment of robust features with the target domain.
Adversarial Bone Length Attack on Action Recognition
Specifically, we restrict the perturbations to the lengths of the skeleton's bones, which allows an adversary to manipulate only approximately 30 effective dimensions.
Evolving Architectures with Gradient Misalignment toward Low Adversarial Transferability
Deep neural network image classifiers are known to be susceptible not only to adversarial examples created for them but even those created for others.
Border basis computation with gradient-weighted normalization
This study proposes the gradient-weighted normalization method for the approximate border basis computation of vanishing ideals, inspired by recent developments in machine learning.
Are DNNs fooled by extremely unrecognizable images?
In this paper, we address the question of whether there can be fooling images with no characteristic pattern of natural objects locally or globally.
Gradient Boosts the Approximate Vanishing Ideal
In the last decade, the approximate vanishing ideal and its basis construction algorithms have been extensively studied in computer algebra and machine learning as a general model to reconstruct the algebraic variety on which noisy data approximately lie.
Spurious Vanishing Problem in Approximate Vanishing Ideal
We further propose a method that takes advantage of the iterative nature of basis construction so that computationally costly operations for coefficient normalization can be circumvented.
Approximate Vanishing Ideal via Data Knotting
The present paper proposes a vanishing ideal that is tolerant to noisy data and also pursued to have a better algebraic structure.
