Sept. 18, 2023, 8:52 a.m. | David Stutz

Blog Archives • David Stutz davidstutz.de

Another alternative to the regular $L_p$-constrained adversarial examples that is additionally less visible than adversarial patches or frames are adversarial transformations such as small crops, rotations and translations. Similar to $L_p$ adversarial examples, adversarial transformations are often less visible unless the original image is available for direct comparison. In this article, I will include a PyTorch implementation and some results against adversarial training.

The post Simple Adversarial Transformations in PyTorch appeared first on David Stutz.

adversarial machine learning article blog comparison deep learning examples image python pytorch simple small

Senior AI/ML Developer

@ Lemon.io | Remote

Earthquake Forecasting Post-doc in ML at the USGS

@ U. S. Geological Survey | Remote, US

Principal Big Data Engineer

@ Kaizen Gaming | Athina, Attica, Greece

Deep Learning Engineer - Autonomous Driving (f./m./div.)

@ Bosch Group | Sequeira, Portugal

FSA (FinTech) - Quantitative Machine Learning Specialist & Software Developer

@ Deloitte | Midrand, South Africa

Data Engineer

@ ZURU | India, Ahmedabad