On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “Defense-GAN”

Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscs.CV

Defense-GAN defends deep neural networks from adversarial attacks using generative models.

problem Vulnerability of deep neural networks to adversarial perturbations.

method Defense-GAN models the distribution of unperturbed images and finds a close output to a given image without adversarial changes.

result Defense-GAN consistently improves over existing defense strategies and works against various attack methods.

adversarial attacks deep neural networks generative models classification defense strategies

2018-05-17abs ↗pdf ↗

Robustifying Models Against Adversarial Attacks by Langevin Dynamicscs.LG

New method defends deep learning models against adversarial attacks.

problem Robustness of deep learning models against adversarial attacks is compromised.

method Adversarial samples are relaxed onto the target class distribution manifold using MALA.

result MALADE outperformed state-of-the-art methods in various attacks.

Adversarial Attacks Deep Learning Robustness Langevin Dynamics Defense-GAN

2018-05-30abs ↗pdf ↗

PuVAE: A Variational Autoencoder to Purify Adversarial Examplescs.LG

PuVAE purifies adversarial examples by projecting them onto class manifolds.

problem Vulnerability of deep neural networks to adversarial attacks.

method PuVAE purifies adversarial examples by projecting them onto the manifold of each class.

result PuVAE purifies adversarial examples effectively without prior knowledge of the attack.

adversarial attacks deep learning variational autoencoder manifold robustness

2019-03-02abs ↗pdf ↗

The Robust Manifold Defense: Adversarial Training using Generative Modelscs.CV

We propose a new type of attack for finding adversarial examples for image classifiers. Our method exploits spanners, i.e. deep neural networks whose input space is low-dimensional and whose output range approximates the set of images of interest. Spanners may be generators of GANs or decoders of VAEs. The key idea in …

2017-12-26abs ↗pdf ↗