Topic

Laurent Amsaleg

Also published under:L. Amsaleg

Affiliation

Inria, Univ Rennes, CNRS, IRISA

Topic

Adversarial Examples,Attack Success,ImageNet,Adversarial Attacks,Adversarial Perturbations,Adversarial Training,Antagonistic Effects,Area Under Receiver Operating Characteristic Curve,Autoencoder Architecture,Bounding Box,Centroid,Class Boundaries,Classification Loss,Clear Image,Constant Learning Rate,Continuous Distribution,Current Image,Data Augmentation,Deep Learning,Deep Neural Network,Dimensional Space,Distance Distribution,Earth Mover’s Distance,Effects Of Perturbations,End Of Each Iteration,Euclidean Space,Extracted Feature Vectors,FC Layer,Fast Gradient Sign Method,Feature Space,Feature Tensor,Figure Of Merit,Focus Of This Work,Form Of Attack,Group Assignment,Group Membership,Hash Function,High-dimensional,Hypersphere,Image Classification,Image Retrieval,Image Space,Incorrect Predictions,Input Space,Integrality Constraints,Interpolation,Joint Learning,Latent Code,Latent Space,Learning Rate,

Biography

Laurent Amsaleg (Member, IEEE) received the Ph.D. degree from the University of Paris 6. He is currently a Senior Researcher with CNRS. He also leads the Linkmedia Research Group, IRISA/INRIA Laboratory, Rennes, France. His research interests include high-dimensional indexing at scale and multimedia analytics, as well as the many facets of the security issues in relation with the processing of extremely large collections of multimedia material. Topics dealing with privacy and adversarial machine learning are therefore central to his work.