Speaker "Alejandra María José Litterio" Details Back
-
Name
Alejandra María José Litterio
-
Company
Eye Capital Ltd
-
Designation
Founder, AI & Deep Learning
Topic
Can a text be attacked? Unwrapping NLP, clashes in meaning, vulnerability and adversarial perturbations
Abstract
In recent years, Deep Learning has fundamentally changed the landscape of several areas in Artificial Intelligence, including speech, computer vision, pattern recognition, and robotics. Following this trend, recent Natural Language Processing research has increasingly focused on the use of new deep learning methods in multiple practical scenarios. Naturally, with advances NLP new threats have emerged. Looking back to the basics, in Linguistics and Interpretation Theory, word order and syntactic structure have a large impact on sentence meaning. Even small perturbation in word order or a morpheme can completely change interpretation. So, the same logic applies to NLP and DL. Could perturbations, barely perceptible by the human eye, make it even harder to generate text adversarial examples? Is there a defence method against attacks that aim to satisfy all the lexical, grammatical, semantic constraints? Is it possible to overcome the new challenges and prevent attacks by malicious users?
Who is this presentation for?
C-Level
Prerequisite knowledge:
ML/ DL /NLP
What you'll learn?
• Overview of NLP • Adversarial attacks: key concepts, background and related work, examples • Models and Toolkits • Practical applications
Profile
Prof. Alejandra M.J. Litterio is a Forensic Linguist, Head of the R&D Department and co-founder at Eye Capital Ltd, a FinTech based in London. She has recently been appointed Vice-President at i-314. She is an expert in NLP leading innovative projects based on the MetaQuant approach and QNLP. She coordinates Eye Capital Quantum Labs, developing new models and frameworks to work in tandem with novel technologies applied to interpreting and coding data in the field of Quantum Computing for the financial markets. Ms. Litterio has been a speaker and panelist internationally. She pursues her Master in Discourse Analysis at Universidad de Buenos Aires. She is actively involved in academia as a researcher and co-director at Centro de Altos Estudios en Tecnología Informática and teaches Computational Linguistics at Universidad Abierta Interamericana.