Real or Fake? Overview on Adversarial Examples
Ciclo de Conferências 2018/2019 - Tecnologia, Empresa e Sociedade
Nowadays, deep learning algorithms tend to be the go-to solution for many machine learning tasks. There are some scenarios where these algorithms are submitted to examples that attempt to force them to predict erroneously. These are called adversarial scenarios found in certain problems such as spam filters, computer security and biometric detection and recognition. Current research indicates that deep learning algorithms are vulnerable to adversarial attacks as any shallow approach, thus obtaining deep networks robust against adversarial examples is a widely open problem. The research on the topic led to a field of Adversarial Learning, where machine learning techniques are used to prevent such attacks. In this presentation, we will overview adversarial learning and explore models and examples for the generation of adversarial examples.
João Nuno Correia (DEISI/ULHT)
João Correia is an Invited Assistant at the University of Coimbra and a researcher of the Computational Design and Visualization Lab. from the Cognitive Media Systems group of the Centre for Informatics and Systems of the same university. He is also an Invited Assistant at the Lusófona University of Lisbon.
He holds a PhD in Information Science and Technology from the University of Coimbra. He also holds a MSc and BS in Informatics Engineering from the University of Coimbra. His main research interests include Evolutionary Computation, Machine Learning, Pattern Recognition, Computer Vision and Computational Creativity. He is involved in different International Program Communities of International conferences of the area of Evolutionary Computation, Artificial Intelligence and Computational Art and Creativity. He was also chair of the International Conference of Evolutionary Art Music and Design conference. Furthermore, he has authored and co-authored several articles on the different International Conferences and journals on Artificial Intelligence and Evolutionary Computation and is involved in national and international projects.