← Back to papers
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 Machine Learning
🧭 Keyword Pioneer — double oracle
🐝 Cross-Pollinator — Artificial Intelligence, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning
🐣 Hot Topic Early Bird — minimax optimization

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

Related papers

Causal Embeddings for Recommendation: An Extended Abstract 2019
Pivotal Relationship Identification: The K-Truss Minimization Problem 2019
Portioning Using Ordinal Preferences: Fairness and Efficiency 2019
Probabilistic Strategy Logic 2019
Multi-Agent Pathfinding with Continuous Time 2019