Papers of the day   All papers

Adversarial Examples Are Not Bugs, They Are Features


Chris Olah: “Adversarial Examples Are Not Bugs, They Are Features” by Ilyas et al is pretty interesting. 📝Paper: 💻Blog: Some quick notes below.

3 replies, 712 likes

Ilya Sutskever: a strange imagenet-like dataset with very wrong-looking labels, yet a model trained on it does totally well on the normal validation set. It's a crime against ML!

10 replies, 526 likes

Lilian Weng: Two most interesting papers I’ve found recently: “the lottery ticket hypothesis” (probably already very famous) and “adversarial examples are not bugs but features”

7 replies, 263 likes

Louise Matsakis: Researchers from MIT now think adversarial examples aren’t AI “hallucinations” after all. The classifier is just “seeing” things that humans can’t. It’s really interesting work!

2 replies, 121 likes

Wojciech Zaremba: Adversarial examples are great features. There is nothing wrong with them. We are just blind to them. Wow.

1 replies, 89 likes

Aleksander Madry: A great piece by @lmatsakis about our recent work on how adversarial examples are actually helpful features! To read more see: and the paper is here:

2 replies, 36 likes

Hamid Eghbal-zadeh: So says we can use adversarial examples to train models that generalise. But says if you train a model with samples from a GAN, it does not generalise, unless you mix it up with real samples!🤔

2 replies, 29 likes

Shreya Shankar: does this stuff interest you? some good papers (in my opinion): * Motivating the Rules of the Game for Adversarial Example Research: (Gilmer et al. 2018) * Adversarial Examples Are Not Bugs, They Are Features: (Ilyas et al. 2019)

1 replies, 28 likes

Thomas Lahore: Adversarial Examples Are Not Bugs, They Are Features "adversarial examples can be directly attributed to the presence of non-robust features ... patterns in the data distribution that are highly predictive, yet brittle and incomprehensible to humans"

0 replies, 24 likes

Daisuke Okanohara: Adversarial examples are not the result of artifacts or overfitting. It is because the learned classifier captures "non-robust" features, which are not incomprehensible by humans but are actually predictive and generalizable.

0 replies, 11 likes

Adam J Calhoun: What if adversarial examples exist because they help the network generalize? And it is simply our puny human minds that aren't able to understand that?

0 replies, 11 likes

午後のarXiv: "Adversarial Examples Are Not Bugs, They Are Features", Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan En…

0 replies, 7 likes

Sai Prasanna: @zacharylipton Adversarial Examples Are Not Bugs, They Are Features

1 replies, 6 likes

Alexander Novikov: Cool! Like furry ear is a feature which can be used to detect cats, adversarial perturbations are features of natural images which can be used to correctly classify both train and test data, except humans don't see it. So adversarial perturbations are human's bugs, not model's.

0 replies, 6 likes

Stefanie Sirén-Heikel: What if adversarial examples aren't bugs, but features? Check out the story on how we might actually really misunderstand how machine learning systems work: and read the paper here:

1 replies, 4 likes

Jason Taylor @NeurIPS2019: Adversarial Examples Are Not Bugs, They Are Features main idea: adversarial examples arise from overfitting on non-robust features. Also shows that adversarial training with flipped labels generalizes to the test set with correct labels

1 replies, 3 likes

Bobby Filar: "Adversarial Examples Are Not Bugs, They Are Features" by @andrew_ilyas, @tsiprasd et al.

0 replies, 3 likes

@reiver ⊼ (Charles Iliya Krempeaux): "Adversarial Examples Are Not Bugs, They Are Features" by Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, Aleksander Madry (machine learning) H/T @QEDanMazur

0 replies, 2 likes

Eric Silverman: This is a really cool paper! Adversarial examples are getting a lot of attention in deep learning research and this paper offers some real insight into the issue

0 replies, 2 likes

Benjamin Singleton: Adversarial Examples Are Not Bugs, They Are Features #DataScience #BigData

0 replies, 1 likes

Hacker News: Adversarial Examples Are Not Bugs, They Are Features: Comments:

0 replies, 1 likes

Hacker News 20: Adversarial Examples Are Not Bugs, They Are Features (

0 replies, 1 likes

Trustworthy ML: Adversarial Examples Are Not Bugs, They Are Features( paper demonstrates that the non-robust features in the dataset account for adversarial examples, and training the model on robust features w/o adversarial training gives a robust model. 1/2

1 replies, 1 likes

HQME: @CBSarrangesme @watch_m3n hmm i'd need to listen to those samples, easy w the data audio -> melspectrograms, encodes frequency decibels and times in a picture

5 replies, 1 likes

Wilfred Hughes: Really interesting paper exploring adversarial inputs to ML models: They conclude: * It's a property of the input data, not the training * You can even train a model on non-robust features and obtain a model that works well on the original input data!

0 replies, 1 likes

Covered Dish People: #1yrago Towards a method for fixing machine learning's persistent and catastrophic blind spots #1yrago Americans with diabetes are forming caravans to buy Canadian insulin at 90% off 13/

1 replies, 1 likes

Chaz Firestone: @IdanAsherBlank @fierycushman but i think that's not quite right. illusions reflect our visual system doing what it's supposed to; a mind that didn't have them would probably end up with some other problems. most people don't think of adversarial images that way (though see 2/n

1 replies, 0 likes


Found on May 09 2019 at

PDF content of a computer science paper: Adversarial Examples Are Not Bugs, They Are Features