Greedy attack and Gumbel attack: generating adversarial examples for discrete data

MaRDI QIDQ4969087zbMATH OpenFDO

Authors Puyudi Yang, Jianbo Chen, Cho-Jui Hsieh, Jane-Ling Wang, Michael Jordan

Publication date 5 October 2020

Full work available at URL https://arxiv.org/abs/1805.12316, https://jmlr.csail.mit.edu/papers/v21/19-569.html

zbMATH Keywords

adversarial attack

Mathematics Subject Classification ID

Computer security (68M25) Learning and adaptive systems in artificial intelligence (68T05) Natural language processing (68T50)

Recommendations

• Attacking neural machine translations via hybrid attention learning
• Adversarial perturbations of deep neural networks
• A robust generative classifier against transfer attacks based on variational auto-encoders
• Black-box adversarial attacks by manipulating image attributes
• Enhancing adversarial attack transferability with multi-scale feature attack

Cites work

• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• Learning to detect and classify malicious executables in the wild
• Neural network credit scoring models
• Simple statistical gradient-following algorithms for connectionist reinforcement learning

Cited in

(4)

• Scalable attack on graph data by injecting vicious nodes
• Giophantus distinguishing attack is a low dimensional learning with errors problem
• Parameter discrepancy hypothesis: adversarial attack for graph data
• A Review of Adversarial Attack and Defense for Classification Methods

Describes a project that uses

Uses Software

• GloVe
• IMDB

This page was built for publication: Greedy attack and Gumbel attack: generating adversarial examples for discrete data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4969087)