The hypothesis in Ilyas et. al. is a special case of a more general principle that is well accepted in the distributional robustness literature — models lack robustness to distribution shift because…
Learn more
You learned about two types of tables: datasets vs. tabulations. Then, you learned about two types of datasets: contiguous vs. non-contiguous. Now, let’s learn about two types of tabulations: formulas…
Learn more
Ilyas et al. report a surprising result: a model trained on adversarial examples is effective on clean data. They suggest this transfer is driven by adverserial examples containing geuinely useful…
Learn more
A Discussion of ‘Adversarial Examples Are Not Bugs, They Are Features’: Two Examples of Useful, Non-Robust Features Ilyas et al. define a feature as a function fff that takes xxx…
Learn more
Last week’s blog post about contiguous vs. non-contiguous datasets was immensely unpopular. I had the most unsubscribes to my blog and newsletter of all time — in more than a…
Learn more
A figure in Ilyas, et. al. that struck me as particularly interesting was the following graph showing a correlation between adversarial transferability between architectures and their tendency to learn similar…
Learn more
Whether you’re a novice data analyst exploring the possibilities of Tableau or a leader with years of experience using VizQL to gain advanced insights—this is your list of key Tableau…
Learn more
We demonstrate that there exist adversarial examples which are just “bugs”: aberrations in the classifier that are not intrinsic properties of the data distribution. In particular, we give a new…
Learn more
Section 3.2 of Ilyas et al. (2019) shows that training a model on only adversarial errors leads to non-trivial generalization on the original test set. We show that these experiments…
Learn more
Introduction In the last few years, reinforcement learning (RL) has made remarkable progress, including beating world-champion Go players, controlling robotic hands, and even painting pictures. One of the key sub-problems…
Learn more
