Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks

Publications associées (30)

Page 3 sur 3

À propos
Confidentialité
Mentions légales

Graph Chatbot

Watermarking-based Defense against Adversarial Attacks on Deep Neural Networks

James Richard Larus, Xiaoting Li, Dinghao Wu, Junjun Zhang

The vulnerability of deep neural networks to adversarial attacks has posed significant threats to real-world applications, especially security-critical ones. Given a well-trained model, slight modifications to the input samples can cause drastic changes in ...

IEEE2021

Learning-based Image Coding: Early Solutions Reviewing and Subjective Quality Evaluation

Touradj Ebrahimi, Pinar Akyazi

Nowadays, image and video are the data types that consume most of the resources of modern communication channels, both in fixed and wireless networks. Thus, it is vital to compress visual data as much as possible, while maintaining some target quality leve ...

SPIE-INT SOC OPTICAL ENGINEERING2021

FeGAN: Scaling Distributed GANs

Rachid Guerraoui, Anne-Marie Kermarrec, Arsany Hany Abdelmessih Guirguis

Existing approaches to distribute Generative Adversarial Networks (GANs) either (i) fail to scale for they typically put the two components of a GAN (the generator and the discriminator) on different machines, inducing significant communication overhead, o ...

2020

Generative adversarial training of product of policies for robust and adaptive movement primitives

Sylvain Calinon, Emmanuel Pignat, Hakan Girgin

In learning from demonstrations, many generative models of trajectories make simplifying assumptions of independence. Correctness is sacrificed in the name of tractability and speed of the learning phase. The ignored dependencies, which are often the kinem ...

2020

TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation

Pascal Fua, Mateusz Kozinski, Leonardo Citraro, Subeesh Vasu

Most state-of-the-art approaches to road extraction from aerial images rely on a CNN trained to label road pixels as foreground and remainder of the image as background. The CNN is usually trained by minimizing pixel-wise losses, which is less than ideal t ...

2020

Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks

Nicolas Henri Bernard Flammarion, Maksym Andriushchenko, Francesco Croce

A large body of research has focused on adversarial attacks which require to modify all input features with small l2- or l∞-norms. In this paper we instead focus on query-efficient sparse attacks in the black-box setting. Our versatile framework, Sparse-RS ...

2020

Learning How to Smile: Expression Video Generation With Conditional Adversarial Recurrent Nets

Wei Wang

While several research studies have focused on analyzing human behavior and, in particular, emotional signals from visual data, the problem of synthesizing face video sequences with specific attributes (e.g. age, facial expressions) received much less atte ...

2020

Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems

Negar Kiyavash

Nonconvex minimax problems appear frequently in emerging machine learning applications, such as generative adversarial networks and adversarial learning. Simple algorithms such as the gradient descent ascent (GDA) are the common practice for solving these ...

2020

Geometry of adversarial robustness of deep networks: methods and applications

Seyed Mohsen Moosavi Dezfooli

We are witnessing a rise in the popularity of using artificial neural networks in many fields of science and technology. Deep neural networks in particular have shown impressive classification performance on a number of challenging benchmarks, generally in ...

EPFL2019

Dual Generator Generative Adversarial Networks for Multi-domain Image-to-Image Translation

Yan Yan, Wei Wang

State-of-the-art methods for image-to-image translation with Generative Adversarial Networks (GANs) can learn a mapping from one domain to another domain using unpaired image data. However, these methods require the training of one specific model for every ...

SPRINGER INTERNATIONAL PUBLISHING AG2019

Page 3 sur 3