Skip to content
conftrace_
2019 IJCAI IJCAI 2019

Adversarial Machine Learning with Double Oracle

Abstract

We aim to improve the general adversarial machine learning solution by introducing the double oracle idea from game theory, which is commonly used to solve a sequential zero-sum game, where the adversarial machine learning problem can be formulated as a zero-sum minimax problem between learner and attacker.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization
🐣 Hot Topic Early Bird - zero-sum game

Authors

Kai Wang

Topics

Artificial Intelligence > Core AI > Game AI Machine Learning > Learning Types > Adversarial Learning Mathematics & Optimization > Optimization > Game Theory Deep Learning > Learning Types > Adversarial Learning

Keywords

adversarial machine learning minimax optimization zero-sum game double oracle minimax problem
Download PDF

More from IJCAI 2019

All IJCAI 2019 papers →
Cautious Rule-Based Collective Inference
The Design of Human Oversight in Autonomous Weapon Systems
A Compliance Checking Framework for DNN Models
AI at the Margins: Data, Decisions, and Inclusive Social Impact
Self-Organizing Incremental Neural Networks for Continual Learning
Evolutionary Learning of Existential Rules