Version 1.0

Lecture: Attacking Text

An Introduction to Adversarial Attacks in NLP

Adversarial examples have been making headlines in the computer vision community for a few years now, but did not seem to have a huge impact in natural language processing until very recently. Small changes to an image, mostly invisible to the human eye, can fool a neural network into classifying a turtle as a gun, or a stop sign as a green light. Of course, a single sentence has significantly fewer features to perturb than a 512x512 colour image, still machines can be fooled by slight rephrasing and exploiting real world biases that have crept into the system.
This talk gives a brief introduction into the technology and dangers of adversarial attacks and delves into the possible implications for testing and employing natural language processing systems.


Day: 2019-11-30
Start time: 11:50
Duration: 00:30
Room: Schellingstr. 3 R153
Track: Computational Linguistics
Language: en



Click here to let us know how you liked this event.

Concurrent Events