PIRSA:18110086

Adversarial Machine Learning

Goodfellow, I. (2018). Adversarial Machine Learning. Perimeter Institute. https://pirsa.org/18110086

Goodfellow, Ian. Adversarial Machine Learning. Perimeter Institute, Nov. 28, 2018, https://pirsa.org/18110086 

          @misc{ pirsa_PIRSA:18110086,
            doi = {10.48660/18110086},
            url = {https://pirsa.org/18110086},
            author = {Goodfellow, Ian},
            keywords = {Other},
            language = {en},
            title = {Adversarial Machine Learning},
            publisher = {Perimeter Institute},
            year = {2018},
            month = {nov},
            note = {PIRSA:18110086 see, \url{https://pirsa.org}}
          }

Ian Goodfellow

Alphabet (United States)

Talk number
PIRSA:18110086
Collection
Talk Type
Subject
Abstract

Most machine learning algorithms involve optimizing a single set of parameters to decrease a single cost function. In adversarial machine learning, two or more "players" each adapt their own parameters to decrease their own cost, in competition with the other players. In some adversarial machine learning algorithms, the algorithm designer contrives this competition between two machine learning models in order to produce a beneficial side effect. For example, the generative adversarial networks framework involves a contrived conflict between a generator network and a discriminator network that results in the generator learning to produce realistic data samples. In other contexts, adversarial machine learning models a real conflict, for example, between spam detectors and spammers. In general, moving machine learning from optimization and a single cost to game theory and multiple costs has led to new insights in many application areas.