paper-with-me

Papers

On the Need for Topology-Aware Generative Models for Manifold-Based Defenses

2019-09-07 · ICLR 2020 1 · Uyeong Jang, Susmit Jha, Somesh Jha

Machine-learning (ML) algorithms or models, especially deep neural networks (DNNs), have shown significant promise in several areas. However, researchers have recently demonstrated that ML algorithms, especially DNNs, are vulnerable to adversarial examples (slightly perturbed samples that cause misclassification). The existence of adversarial examples has hindered the deployment of ML algorithms in safety-critical sectors, such as security. Several defenses for adversarial examples exist in the literature. One of the important classes of defenses are manifold-based defenses, where a sample is ``pulled back" into the data manifold before classifying. These defenses rely on the assumption that data lie in a manifold of a lower dimension than the input space. These defenses use a generative model to approximate the input distribution. In this paper, we investigate the following question: do the generative models used in manifold-based defenses need to be topology-aware? We suggest the answer is yes, and we provide theoretical and empirical evidence to support our claim.

📄 PDF Abstract BibTeX arXiv:1909.03334

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

Topo Sampler: A Topology Constrained Noise Sampling for GANs

2020-10-10 · NeurIPS Workshop TDA_and_Beyond 2020 12 · Adrish Dey, Sayantan Das

This work studies disconnected manifold learning in generative models in the light of point-set topology and persistent homology. Under this formalism, the topological similarity of latent space in generative models with…

Approximate Manifold Defense Against Multiple Adversarial Perturbations

2020-04-05 · Jay Nandy, Wynne Hsu, Mong Li Lee

Existing defenses against adversarial attacks are typically tailored to a specific perturbation type. Using adversarial training to defend against multiple types of perturbation requires expensive adversarial examples fr…

Adversarial Robustnessimage-classificationImage Classification

MAD-VAE: Manifold Awareness Defense Variational Autoencoder

2020-10-31 · Frederick Morlock, Dingsu Wang

Although deep generative models such as Defense-GAN and Defense-VAE have made significant progress in terms of adversarial defenses of image classification neural networks, several methods have been found to circumvent t…

image-classificationImage Classification

Neural Implicit Manifold Learning for Topology-Aware Density Estimation

2022-06-22 · Brendan Leigh Ross, Gabriel Loaiza-Ganem, Anthony L. Caterini, Jesse C. Cresswell

Natural data observed in $\mathbb{R}^n$ is often constrained to an $m$-dimensional manifold $\mathcal{M}$, where $m < n$. This work focuses on the task of building theoretically principled generative models for such data…

Density Estimation

On Breaking Deep Generative Model-based Defenses and Beyond

2020-01-01 · ICML 2020 1 · Yanzhi Chen, Renjie Xie, Zhanxing Zhu

Deep neural networks have been proven to be vulnerable to the so-called adversarial attacks. Recently there have been efforts to defend such attacks with deep generative models. These defenses often involve an inversion …